diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 92fcf5a4..dc3414cb 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -40,6 +40,17 @@ repos:
     hooks:
       - id: python-check-blanket-noqa
       - id: python-use-type-annotations
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+      - id: black
+        language_version: python3.10
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: "1.13.0"
+    hooks:
+      - id: blacken-docs
+        additional_dependencies:
+          - black>=23.3
   - repo: https://github.com/charliermarsh/ruff-pre-commit
     rev: v0.0.270
     hooks:
diff --git a/poetry.lock b/poetry.lock
index b488532a..e490ad19 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1091,4 +1091,4 @@ all = ["polars"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "b263fee7e129a0ec0597becc2f34ca0ecd7820d4fb9c04b438292fa2253787f9"
+content-hash = "799925190004c1d5bd0aa5b3e7e7ca27cc9b1867f7d00091da398c5b0db714b3"
diff --git a/pyproject.toml b/pyproject.toml
index b1e3e028..0ab96cf7 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -48,7 +48,7 @@ docformatter = { extras = ["tomli"], version = "^1.7" }
 pre-commit = "^3.3"
 pylint = "^2.17"
 pytest = "^7.3"
-pytest-cov = "^4.0"
+pytest-cov = "^4.1"
 pytest-timeout = "^2.1"
 ruff = "^0.0,>=0.0.270"
 
diff --git a/src/redcat/base.py b/src/redcat/base.py
index 2449c804..a99ac2d2 100644
--- a/src/redcat/base.py
+++ b/src/redcat/base.py
@@ -41,7 +41,7 @@ def clone(self) -> TBatch:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -77,7 +77,7 @@ def allclose(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -100,7 +100,7 @@ def equal(self, other: Any) -> bool:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -127,7 +127,7 @@ def permute_along_batch(self, permutation: Sequence[int] | Tensor) -> TBatch:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -152,7 +152,7 @@ def permute_along_batch_(self, permutation: Sequence[int] | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -179,7 +179,7 @@ def shuffle_along_batch(self, generator: torch.Generator | None = None) -> TBatc
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -203,7 +203,7 @@ def shuffle_along_batch_(self, generator: torch.Generator | None = None) -> None
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -241,7 +241,7 @@ def append(self, other: BaseBatch) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -271,7 +271,7 @@ def chunk_along_batch(self, chunks: int) -> tuple[TBatch, ...]:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -304,14 +304,12 @@ def extend(self, other: Iterable[BaseBatch]) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(torch.ones(2, 3))
-            >>> batch.extend(
-            ...     [BatchedTensor(torch.zeros(1, 3)), BatchedTensor(torch.full((1, 3), 2.0))]
-            ... )
+            >>> batch.extend([BatchedTensor(torch.zeros(1, 3)), BatchedTensor(torch.full((1, 3), 2.0))])
             >>> batch.data
             tensor([[1., 1., 1.],
                     [1., 1., 1.],
@@ -334,7 +332,7 @@ def index_select_along_batch(self, index: Tensor | Sequence[int]) -> BaseBatch:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -363,7 +361,7 @@ def select_along_batch(self, index: int) -> T:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -389,7 +387,7 @@ def slice_along_batch(self, start: int = 0, stop: int | None = None, step: int =
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -421,7 +419,7 @@ def split_along_batch(self, split_size_or_sections: int | Sequence[int]) -> tupl
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -450,7 +448,7 @@ def get_num_minibatches(self, batch_size: int, drop_last: bool = False) -> int:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -490,7 +488,7 @@ def to_minibatches(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
diff --git a/src/redcat/batchdict.py b/src/redcat/batchdict.py
index 6a99c23c..a7479a2b 100644
--- a/src/redcat/batchdict.py
+++ b/src/redcat/batchdict.py
@@ -139,7 +139,7 @@ def permute_along_seq(self, permutation: Sequence[int] | Tensor) -> TBatchDict:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -181,7 +181,7 @@ def permute_along_seq_(self, permutation: Sequence[int] | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -222,7 +222,7 @@ def shuffle_along_seq(self, generator: torch.Generator | None = None) -> TBatchD
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -264,7 +264,7 @@ def shuffle_along_seq_(self, generator: torch.Generator | None = None) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -324,7 +324,7 @@ def cat_along_seq(self, batches: BatchDict | Sequence[BatchDict]) -> TBatchDict:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -335,9 +335,7 @@ def cat_along_seq(self, batches: BatchDict | Sequence[BatchDict]) -> TBatchDict:
             ...     }
             ... )
             >>> b.cat_along_seq(
-            ...     BatchDict(
-            ...         {"key1": BatchedTensorSeq(torch.tensor([[10, 11, 12], [20, 21, 22]]))}
-            ...     )
+            ...     BatchDict({"key1": BatchedTensorSeq(torch.tensor([[10, 11, 12], [20, 21, 22]]))})
             ... )
             BatchDict(
               (key1) tensor([[ 0,  1,  2,  3,  4, 10, 11, 12],
@@ -366,7 +364,7 @@ def cat_along_seq_(self, batches: BatchDict | Sequence[BatchDict]) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchDict, BatchList, BatchedTensorSeq
@@ -377,9 +375,7 @@ def cat_along_seq_(self, batches: BatchDict | Sequence[BatchDict]) -> None:
             ...     }
             ... )
             >>> b.cat_along_seq_(
-            ...     BatchDict(
-            ...         {"key1": BatchedTensorSeq(torch.tensor([[10, 11, 12], [20, 21, 22]]))}
-            ...     )
+            ...     BatchDict({"key1": BatchedTensorSeq(torch.tensor([[10, 11, 12], [20, 21, 22]]))})
             ... )
             >>> b
             BatchDict(
diff --git a/src/redcat/batchlist.py b/src/redcat/batchlist.py
index d95c0d49..b9fc6ce7 100644
--- a/src/redcat/batchlist.py
+++ b/src/redcat/batchlist.py
@@ -160,7 +160,7 @@ def apply(self, fn: Callable[[T], T]) -> TBatchList:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchList
@@ -183,7 +183,7 @@ def apply_(self, fn: Callable[[T], T]) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchList
diff --git a/src/redcat/datapipes/iter/batching.py b/src/redcat/datapipes/iter/batching.py
index 1912e6e2..4a23951f 100644
--- a/src/redcat/datapipes/iter/batching.py
+++ b/src/redcat/datapipes/iter/batching.py
@@ -35,7 +35,7 @@ class MiniBatcherIterDataPipe(IterDataPipe[BaseBatch[T]]):
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> from torch.utils.data.datapipes.iter import IterableWrapper
diff --git a/src/redcat/datapipes/iter/joining.py b/src/redcat/datapipes/iter/joining.py
index 190924f6..295574a5 100644
--- a/src/redcat/datapipes/iter/joining.py
+++ b/src/redcat/datapipes/iter/joining.py
@@ -31,7 +31,7 @@ class BatchExtenderIterDataPipe(IterDataPipe[BaseBatch[T]]):
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> from torch.utils.data.datapipes.iter import IterableWrapper
diff --git a/src/redcat/datapipes/iter/shuffling.py b/src/redcat/datapipes/iter/shuffling.py
index ff6c6982..487a64fb 100644
--- a/src/redcat/datapipes/iter/shuffling.py
+++ b/src/redcat/datapipes/iter/shuffling.py
@@ -26,7 +26,7 @@ class BatchShufflerIterDataPipe(IterDataPipe[BaseBatch[T]]):
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> from torch.utils.data.datapipes.iter import IterableWrapper
diff --git a/src/redcat/tensor.py b/src/redcat/tensor.py
index f9ecf6ab..f2724ebb 100644
--- a/src/redcat/tensor.py
+++ b/src/redcat/tensor.py
@@ -95,7 +95,7 @@ def dim(self) -> int:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -112,7 +112,7 @@ def ndimension(self) -> int:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -129,7 +129,7 @@ def numel(self) -> int:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -158,7 +158,7 @@ def contiguous(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -183,7 +183,7 @@ def is_contiguous(self, memory_format: torch.memory_format = torch.contiguous_fo
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -205,12 +205,12 @@ def to(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(torch.ones(2, 3))
-            >>> batch_cuda = batch.to(device=torch.device('cuda:0'))
+            >>> batch_cuda = batch.to(device=torch.device("cuda:0"))
             >>> batch_bool = batch.to(dtype=torch.bool)
             >>> batch_bool
             tensor([[True, True, True],
@@ -234,7 +234,7 @@ def clone(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -261,7 +261,7 @@ def empty_like(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -287,7 +287,7 @@ def full_like(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -324,7 +324,7 @@ def new_full(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -370,7 +370,7 @@ def new_ones(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -416,7 +416,7 @@ def new_zeros(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -454,7 +454,7 @@ def ones_like(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -481,7 +481,7 @@ def zeros_like(self, *args, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -534,7 +534,7 @@ def eq(self, other: BatchedTensor | Tensor | bool | int | float) -> TBatchedTens
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -572,7 +572,7 @@ def ge(self, other: BatchedTensor | Tensor | bool | int | float) -> TBatchedTens
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -602,7 +602,7 @@ def gt(self, other: BatchedTensor | Tensor | bool | int | float) -> TBatchedTens
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -631,12 +631,12 @@ def isinf(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
-            ...     torch.tensor([[1.0, 0.0, float('inf')], [-1.0, -2.0, float('-inf')]])
+            ...     torch.tensor([[1.0, 0.0, float("inf")], [-1.0, -2.0, float("-inf")]])
             ... )
             >>> batch.isinf()
             tensor([[False, False, True],
@@ -655,12 +655,12 @@ def isneginf(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
-            ...     torch.tensor([[1.0, 0.0, float('inf')], [-1.0, -2.0, float('-inf')]])
+            ...     torch.tensor([[1.0, 0.0, float("inf")], [-1.0, -2.0, float("-inf")]])
             ... )
             >>> batch.isneginf()
             tensor([[False, False, False],
@@ -679,12 +679,12 @@ def isposinf(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
-            ...     torch.tensor([[1.0, 0.0, float('inf')], [-1.0, -2.0, float('-inf')]])
+            ...     torch.tensor([[1.0, 0.0, float("inf")], [-1.0, -2.0, float("-inf")]])
             ... )
             >>> batch.isposinf()
             tensor([[False, False,   True],
@@ -702,12 +702,12 @@ def isnan(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
-            ...     torch.tensor([[1.0, 0.0, float('nan')], [float('nan'), -2.0, -1.0]])
+            ...     torch.tensor([[1.0, 0.0, float("nan")], [float("nan"), -2.0, -1.0]])
             ... )
             >>> batch.isnan()
             tensor([[False, False,  True],
@@ -727,7 +727,7 @@ def le(self, other: BatchedTensor | Tensor | bool | int | float) -> TBatchedTens
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -757,7 +757,7 @@ def lt(self, other: BatchedTensor | Tensor | bool | int | float) -> TBatchedTens
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -792,7 +792,7 @@ def bool(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -810,7 +810,7 @@ def double(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -828,7 +828,7 @@ def float(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -846,7 +846,7 @@ def int(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -864,7 +864,7 @@ def long(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -932,7 +932,7 @@ def add(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -966,7 +966,7 @@ def add_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1005,7 +1005,7 @@ def div(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1042,7 +1042,7 @@ def div_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1073,7 +1073,7 @@ def fmod(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1099,7 +1099,7 @@ def fmod_(self, divisor: BatchedTensor | Tensor | int | float) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1127,7 +1127,7 @@ def mul(self, other: BatchedTensor | Tensor | int | float) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1157,7 +1157,7 @@ def mul_(self, other: BatchedTensor | Tensor | int | float) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1179,7 +1179,7 @@ def neg(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1216,7 +1216,7 @@ def sub(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1249,7 +1249,7 @@ def sub_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1280,7 +1280,7 @@ def cumsum(self, dim: int, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1300,7 +1300,7 @@ def cumsum_(self, dim: int, **kwargs) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1325,7 +1325,7 @@ def cumsum_along_batch(self, **kwargs) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1341,7 +1341,7 @@ def cumsum_along_batch_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1368,7 +1368,7 @@ def logcumsumexp(self, dim: int) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1388,7 +1388,7 @@ def logcumsumexp_(self, dim: int) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1412,7 +1412,7 @@ def logcumsumexp_along_batch(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1432,7 +1432,7 @@ def logcumsumexp_along_batch_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1469,7 +1469,7 @@ def permute_along_dim(self, permutation: Sequence[int] | Tensor, dim: int) -> TB
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1499,7 +1499,7 @@ def permute_along_dim_(self, permutation: Sequence[int] | Tensor, dim: int) -> N
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1532,7 +1532,7 @@ def shuffle_along_dim(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1561,7 +1561,7 @@ def shuffle_along_dim_(self, dim: int, generator: torch.Generator | None = None)
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1603,7 +1603,7 @@ def sort(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1642,7 +1642,7 @@ def sort_along_batch(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1668,7 +1668,7 @@ def abs(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1686,7 +1686,7 @@ def abs_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1720,7 +1720,7 @@ def clamp(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1759,7 +1759,7 @@ def clamp_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1790,7 +1790,7 @@ def exp(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1808,7 +1808,7 @@ def exp_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1829,7 +1829,7 @@ def log(self) -> BatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1849,7 +1849,7 @@ def log_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1872,11 +1872,13 @@ def log1p(self) -> BatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> batch = BatchedTensor(torch.tensor([[0.0, 1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0, 9.0]]))
+            >>> batch = BatchedTensor(
+            ...     torch.tensor([[0.0, 1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0, 9.0]])
+            ... )
             >>> batch.log1p()
             tensor([[0.0000, 0.6931, 1.0986, 1.3863, 1.6094],
                     [1.7918, 1.9459, 2.0794, 2.1972, 2.3026]], batch_dim=0)
@@ -1890,7 +1892,7 @@ def log1p_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1917,7 +1919,7 @@ def maximum(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1941,7 +1943,7 @@ def minimum(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1967,7 +1969,7 @@ def pow(self, exponent: int | float | BatchedTensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -1991,7 +1993,7 @@ def pow_(self, exponent: int | float | BatchedTensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2013,7 +2015,7 @@ def rsqrt(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2030,7 +2032,7 @@ def rsqrt_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2051,7 +2053,7 @@ def sqrt(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2069,7 +2071,7 @@ def sqrt_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2098,7 +2100,7 @@ def max(self, *args, **kwargs) -> Tensor | torch.return_types.max:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2129,19 +2131,17 @@ def max_along_batch(self, keepdim: bool = False) -> torch.return_types.max:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])
-            ... ).max_along_batch()
+            >>> BatchedTensor(torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])).max_along_batch()
             torch.return_types.max(
             values=tensor([4, 9]),
             indices=tensor([4, 4]))
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])
-            ... ).max_along_batch(keepdim=True)
+            >>> BatchedTensor(torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])).max_along_batch(
+            ...     keepdim=True
+            ... )
             torch.return_types.max(
             values=tensor([[4], [9]]),
             indices=tensor([[4], [4]]))
@@ -2160,7 +2160,7 @@ def mean(self, *args, **kwargs) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2187,7 +2187,7 @@ def mean_along_batch(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2214,7 +2214,7 @@ def median(self, *args, **kwargs) -> Tensor | torch.return_types.median:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2247,7 +2247,7 @@ def median_along_batch(self, keepdim: bool = False) -> torch.return_types.median
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2273,7 +2273,7 @@ def min(self, *args, **kwargs) -> Tensor | torch.return_types.min:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2304,19 +2304,17 @@ def min_along_batch(self, keepdim: bool = False) -> torch.return_types.min:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])
-            ... ).min_along_batch()
+            >>> BatchedTensor(torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])).min_along_batch()
             torch.return_types.min(
             values=tensor([0, 5]),
             indices=tensor([0, 0]))
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])
-            ... ).min_along_batch(keepdim=True)
+            >>> BatchedTensor(torch.tensor([[0, 5], [1, 6], [2, 7], [3, 8], [4, 9]])).min_along_batch(
+            ...     keepdim=True
+            ... )
             torch.return_types.min(
             values=tensor([[0], [5]]),
             indices=tensor([[0], [0]]))
@@ -2335,21 +2333,19 @@ def nanmean(self, *args, **kwargs) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmean()
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmean()
             tensor(4.0)
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmean(dim=1)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmean(
+            ...     dim=1
+            ... )
             tensor([2.0, 6.5])
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmean(dim=1, keepdim=True)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmean(
+            ...     dim=1, keepdim=True
+            ... )
             tensor([[2.0], [6.5]])
         """
         return torch.nanmean(self, *args, **kwargs)
@@ -2368,16 +2364,16 @@ def nanmean_along_batch(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> BatchedTensor(
-            ...     torch.tensor([[0., 5.], [1., 6.], [2., 7.], [3., 8.], [4., float("nan")]])
+            ...     torch.tensor([[0.0, 5.0], [1.0, 6.0], [2.0, 7.0], [3.0, 8.0], [4.0, float("nan")]])
             ... ).nanmean_along_batch()
             tensor([2.0, 6.5])
             >>> BatchedTensor(
-            ...     torch.tensor([[0., 5.], [1., 6.], [2., 7.], [3., 8.], [4., float("nan")]])
+            ...     torch.tensor([[0.0, 5.0], [1.0, 6.0], [2.0, 7.0], [3.0, 8.0], [4.0, float("nan")]])
             ... ).nanmean_along_batch(keepdim=True)
             tensor([[2.0, 6.5]])
         """
@@ -2399,23 +2395,21 @@ def nanmedian(self, *args, **kwargs) -> Tensor | torch.return_types.nanmedian:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmedian()
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmedian()
             tensor(4.0)
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmedian(dim=1)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmedian(
+            ...     dim=1
+            ... )
             torch.return_types.nanmedian(
             values=tensor([2., 6.]),
             indices=tensor([2, 1]))
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nanmedian(dim=1, keepdim=True)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nanmedian(
+            ...     dim=1, keepdim=True
+            ... )
             torch.return_types.nanmedian(
             values=tensor([[2.], [6.]]),
             indices=tensor([[2], [1]]))
@@ -2438,12 +2432,12 @@ def nanmedian_along_batch(self, keepdim: bool = False) -> torch.return_types.nan
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> BatchedTensor(
-            ...     torch.tensor([[0., 5.], [1., 6.], [2., 7.], [3., 8.], [4., float("nan")]])
+            ...     torch.tensor([[0.0, 5.0], [1.0, 6.0], [2.0, 7.0], [3.0, 8.0], [4.0, float("nan")]])
             ... ).nanmedian_along_batch()
             torch.return_types.nanmedian(
             values=tensor([2., 6.]),
@@ -2463,21 +2457,17 @@ def nansum(self, *args, **kwargs) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nansum()
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nansum()
             tensor(36.)
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nansum(dim=1)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nansum(dim=1)
             tensor([10., 26.])
-            >>> BatchedTensor(
-            ...     torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])
-            ... ).nansum(dim=1, keepdim=True)
+            >>> BatchedTensor(torch.tensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, float("nan")]])).nansum(
+            ...     dim=1, keepdim=True
+            ... )
             tensor([[10.], [26.]])
         """
         return torch.nansum(self, *args, **kwargs)
@@ -2496,12 +2486,12 @@ def nansum_along_batch(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> BatchedTensor(
-            ...     torch.tensor([[0., 5.], [1., 6.], [2., 7.], [3., 8.], [4., float("nan")]])
+            ...     torch.tensor([[0.0, 5.0], [1.0, 6.0], [2.0, 7.0], [3.0, 8.0], [4.0, float("nan")]])
             ... ).nansum_along_batch()
             tensor([20., 26.])
         """
@@ -2519,21 +2509,17 @@ def prod(self, *args, **kwargs) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])
-            ... ).prod()
+            >>> BatchedTensor(torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])).prod()
             tensor(362880)
-            >>> BatchedTensor(
-            ...     torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])
-            ... ).prod(dim=1)
+            >>> BatchedTensor(torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])).prod(dim=1)
             tensor([ 120, 3024])
-            >>> BatchedTensor(
-            ...     torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])
-            ... ).prod(dim=1, keepdim=True)
+            >>> BatchedTensor(torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])).prod(
+            ...     dim=1, keepdim=True
+            ... )
             tensor([[ 120], [3024]])
         """
         return torch.prod(self, *args, **kwargs)
@@ -2552,17 +2538,15 @@ def prod_along_batch(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
-            >>> BatchedTensor(
-            ...     torch.tensor([[1, 6], [2, 7], [3, 8], [4, 9], [5, 1]])
-            ... ).prod_along_batch()
+            >>> BatchedTensor(torch.tensor([[1, 6], [2, 7], [3, 8], [4, 9], [5, 1]])).prod_along_batch()
             tensor([ 120, 3024])
-            >>> BatchedTensor(
-            ...     torch.tensor([[1, 6], [2, 7], [3, 8], [4, 9], [5, 1]])
-            ... ).prod_along_batch(keepdim=True)
+            >>> BatchedTensor(torch.tensor([[1, 6], [2, 7], [3, 8], [4, 9], [5, 1]])).prod_along_batch(
+            ...     keepdim=True
+            ... )
             tensor([[ 120, 3024]])
         """
         return self.prod(dim=self._batch_dim, keepdim=keepdim)
@@ -2579,7 +2563,7 @@ def sum(self, *args, **kwargs) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2606,7 +2590,7 @@ def sum_along_batch(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2628,7 +2612,7 @@ def acos(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2646,7 +2630,7 @@ def acos_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2668,7 +2652,7 @@ def acosh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2689,7 +2673,7 @@ def acosh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2710,7 +2694,7 @@ def asin(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2728,7 +2712,7 @@ def asin_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2750,7 +2734,7 @@ def asinh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2769,7 +2753,7 @@ def asinh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2790,7 +2774,7 @@ def atan(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2808,7 +2792,7 @@ def atan_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2829,7 +2813,7 @@ def atanh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2847,7 +2831,7 @@ def atanh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2868,7 +2852,7 @@ def cos(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
@@ -2889,7 +2873,7 @@ def cos_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
@@ -2913,7 +2897,7 @@ def cosh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2931,7 +2915,7 @@ def cosh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -2952,7 +2936,7 @@ def sin(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
@@ -2973,7 +2957,7 @@ def sin_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
@@ -2997,7 +2981,7 @@ def sinh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3015,7 +2999,7 @@ def sinh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3036,17 +3020,14 @@ def tan(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
             ...     torch.tensor(
-            ...         [
-            ...             [0.0, 0.25 * math.pi, math.pi],
-            ...             [2 * math.pi, 1.75 * math.pi, -0.25 * math.pi]
-            ...         ]
+            ...         [[0.0, 0.25 * math.pi, math.pi], [2 * math.pi, 1.75 * math.pi, -0.25 * math.pi]]
             ...     )
             ... )
             >>> batch.tan()
@@ -3062,17 +3043,14 @@ def tan_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> import math
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(
             ...     torch.tensor(
-            ...         [
-            ...             [0.0, 0.25 * math.pi, math.pi],
-            ...             [2 * math.pi, 1.75 * math.pi, -0.25 * math.pi]
-            ...         ]
+            ...         [[0.0, 0.25 * math.pi, math.pi], [2 * math.pi, 1.75 * math.pi, -0.25 * math.pi]]
             ...     )
             ... )
             >>> batch.tan_()
@@ -3091,7 +3069,7 @@ def tanh(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3109,7 +3087,7 @@ def tanh_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3142,7 +3120,7 @@ def logical_and(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3171,7 +3149,7 @@ def logical_and_(self, other: BatchedTensor | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3201,7 +3179,7 @@ def logical_not(self) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3222,7 +3200,7 @@ def logical_not_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3252,7 +3230,7 @@ def logical_or(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3280,7 +3258,7 @@ def logical_or_(self, other: BatchedTensor | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3314,7 +3292,7 @@ def logical_xor(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3342,7 +3320,7 @@ def logical_xor_(self, other: BatchedTensor | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3399,7 +3377,7 @@ def cat(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3429,14 +3407,12 @@ def cat_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(torch.tensor([[0, 1, 2], [4, 5, 6]]))
-            >>> batch.cat_(
-            ...     BatchedTensor(torch.tensor([[10, 11, 12], [13, 14, 15]]))
-            ... )
+            >>> batch.cat_(BatchedTensor(torch.tensor([[10, 11, 12], [13, 14, 15]])))
             >>> batch
             tensor([[ 0,  1,  2],
                     [ 4,  5,  6],
@@ -3461,7 +3437,7 @@ def cat_along_batch(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3500,14 +3476,12 @@ def cat_along_batch_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
             >>> batch = BatchedTensor(torch.tensor([[0, 1, 2], [4, 5, 6]]))
-            >>> batch.cat_along_batch_(
-            ...     BatchedTensor(torch.tensor([[10, 11, 12], [13, 14, 15]]))
-            ... )
+            >>> batch.cat_along_batch_(BatchedTensor(torch.tensor([[10, 11, 12], [13, 14, 15]])))
             >>> batch
             tensor([[ 0,  1,  2],
                     [ 4,  5,  6],
@@ -3545,7 +3519,7 @@ def chunk(self, chunks: int, dim: int = 0) -> tuple[TBatchedTensor, ...]:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3577,7 +3551,7 @@ def index_select(self, dim: int, index: Tensor | Sequence[int]) -> TBatchedTenso
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3615,7 +3589,7 @@ def masked_fill(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3657,7 +3631,7 @@ def select(self, dim: int, index: int) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3699,7 +3673,7 @@ def slice_along_dim(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3741,7 +3715,7 @@ def split(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3772,7 +3746,7 @@ def take_along_batch(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3802,7 +3776,7 @@ def take_along_dim(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3834,7 +3808,7 @@ def unsqueeze(self, dim: int) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3871,7 +3845,7 @@ def view(self, *shape: tuple[int, ...]) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3903,7 +3877,7 @@ def view_as(self, other: BatchedTensor | Tensor) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3947,7 +3921,7 @@ def apply(self, fn: Callable[[Tensor], Tensor]) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
@@ -3975,7 +3949,7 @@ def apply_(self, fn: Callable[[Tensor], Tensor]) -> TBatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensor
diff --git a/src/redcat/tensorseq.py b/src/redcat/tensorseq.py
index 5b751cf0..88cd1efc 100644
--- a/src/redcat/tensorseq.py
+++ b/src/redcat/tensorseq.py
@@ -124,7 +124,7 @@ def new_full(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -179,7 +179,7 @@ def new_ones(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -234,7 +234,7 @@ def new_zeros(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -275,7 +275,7 @@ def from_seq_batch(cls, data: Any, **kwargs) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -360,7 +360,7 @@ def cumsum_along_seq(self, **kwargs) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -377,7 +377,7 @@ def cumsum_along_seq_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -401,7 +401,7 @@ def logcumsumexp_along_seq(self) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -418,7 +418,7 @@ def logcumsumexp_along_seq_(self) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -444,7 +444,7 @@ def permute_along_seq(self, permutation: Sequence[int] | Tensor) -> BatchedTenso
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -466,7 +466,7 @@ def permute_along_seq_(self, permutation: Sequence[int] | Tensor) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -491,7 +491,7 @@ def shuffle_along_seq(self, generator: torch.Generator | None = None) -> Batched
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -511,7 +511,7 @@ def shuffle_along_seq_(self, generator: torch.Generator | None = None) -> None:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -547,7 +547,7 @@ def sort_along_seq(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -602,7 +602,7 @@ def max_along_seq(self, keepdim: bool = False) -> torch.return_types.max:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -632,7 +632,7 @@ def mean_along_seq(self, keepdim: bool = False) -> BatchedTensor | BatchedTensor
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -659,7 +659,7 @@ def median_along_seq(self, keepdim: bool = False) -> torch.return_types.median:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -684,7 +684,7 @@ def min_along_seq(self, keepdim: bool = False) -> torch.return_types.min:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -713,7 +713,7 @@ def nanmean_along_seq(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -744,7 +744,7 @@ def nanmedian_along_seq(self, keepdim: bool = False) -> torch.return_types.nanme
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -771,7 +771,7 @@ def nansum_along_seq(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -796,15 +796,15 @@ def prod_along_seq(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
             >>> BatchedTensorSeq(torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])).prod_along_seq()
             tensor([ 120, 3024])
-            >>> BatchedTensorSeq(
-            ...     torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])
-            ... ).prod_along_seq(keepdim=True)
+            >>> BatchedTensorSeq(torch.tensor([[1, 2, 3, 4, 5], [6, 7, 8, 9, 1]])).prod_along_seq(
+            ...     keepdim=True
+            ... )
             tensor([[ 120], [3024]])
         """
         return self.prod(dim=self._seq_dim, keepdim=keepdim)
@@ -824,7 +824,7 @@ def sum_along_seq(self, keepdim: bool = False) -> Tensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -852,7 +852,7 @@ def align_as(self, other: BatchedTensorSeq) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -900,7 +900,7 @@ def align_to_batch_seq(self) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -923,7 +923,7 @@ def align_to_seq_batch(self) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -957,7 +957,7 @@ def cat_along_seq(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -967,7 +967,9 @@ def cat_along_seq(
             tensor([[ 0,  1,  2, 10, 11],
                     [ 4,  5,  6, 12, 13]], batch_dim=0, seq_dim=1)
             >>> BatchedTensorSeq(
-            ...     torch.tensor([[0, 4], [1, 5], [2, 6]]), batch_dim=1, seq_dim=0,
+            ...     torch.tensor([[0, 4], [1, 5], [2, 6]]),
+            ...     batch_dim=1,
+            ...     seq_dim=0,
             ... ).cat_along_seq(
             ...     [
             ...         BatchedTensorSeq(torch.tensor([[10, 12], [11, 13]]), batch_dim=1, seq_dim=0),
@@ -998,19 +1000,19 @@ def cat_along_seq_(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
             >>> batch = BatchedTensorSeq(torch.tensor([[0, 1, 2], [4, 5, 6]]))
-            >>> batch.cat_along_seq_(
-            ...     BatchedTensorSeq(torch.tensor([[10, 11], [12, 13]]))
-            ... )
+            >>> batch.cat_along_seq_(BatchedTensorSeq(torch.tensor([[10, 11], [12, 13]])))
             >>> batch
             tensor([[ 0,  1,  2, 10, 11],
                     [ 4,  5,  6, 12, 13]], batch_dim=0, seq_dim=1)
             >>> batch = BatchedTensorSeq(
-            ...     torch.tensor([[0, 4], [1, 5], [2, 6]]), batch_dim=1, seq_dim=0,
+            ...     torch.tensor([[0, 4], [1, 5], [2, 6]]),
+            ...     batch_dim=1,
+            ...     seq_dim=0,
             ... )
             >>> batch.cat_along_seq(
             ...     [
@@ -1041,7 +1043,7 @@ def chunk_along_seq(self, chunks: int) -> tuple[BatchedTensorSeq, ...]:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1066,7 +1068,7 @@ def index_select_along_seq(self, index: Tensor | Sequence[int]) -> BatchedTensor
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1101,7 +1103,7 @@ def repeat_along_seq(self, repeats: int) -> BatchedTensorSeq:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1126,7 +1128,7 @@ def select_along_seq(self, index: int) -> BatchedTensor:
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1157,7 +1159,7 @@ def slice_along_seq(
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1192,7 +1194,7 @@ def take_along_seq(self, indices: BaseBatch | Tensor | Sequence) -> BatchedTenso
 
         Example usage:
 
-        .. code-block:: python
+        .. code-block:: pycon
 
             >>> import torch
             >>> from redcat import BatchedTensorSeq
@@ -1437,7 +1439,7 @@ def from_sequences(
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> import redcat
diff --git a/src/redcat/utils/format.py b/src/redcat/utils/format.py
index 55771eaa..b388f36c 100644
--- a/src/redcat/utils/format.py
+++ b/src/redcat/utils/format.py
@@ -23,10 +23,10 @@ def str_mapping(mapping: Mapping, sorted_keys: bool = False, num_spaces: int = 2
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> from redcat.utils.format import str_mapping
-        >>> str_mapping({'key1': 'abc', 'key2': 'something\nelse'})
+        >>> str_mapping({"key1": "abc", "key2": "something\nelse"})
         (key1) abc
         (key2) something
           else
diff --git a/src/redcat/utils/tensor.py b/src/redcat/utils/tensor.py
index 44628887..e3ce5a34 100644
--- a/src/redcat/utils/tensor.py
+++ b/src/redcat/utils/tensor.py
@@ -39,7 +39,7 @@ def align_to_batch_first(tensor: Tensor, batch_dim: int) -> Tensor:
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> from redcat.utils.tensor import align_to_batch_first
@@ -134,7 +134,7 @@ def compute_batch_seq_permutation(
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> from redcat.utils.tensor import compute_batch_seq_permutation
         >>> compute_batch_seq_permutation(5, 0, 1, 1, 0)
@@ -176,7 +176,7 @@ def get_available_devices() -> tuple[str, ...]:
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> from redcat.utils.tensor import get_available_devices
         >>> get_available_devices()
@@ -208,7 +208,7 @@ def get_torch_generator(
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> import torch
         >>> from redcat.utils.tensor import get_torch_generator
@@ -245,7 +245,7 @@ def permute_along_dim(tensor: Tensor, permutation: Tensor, dim: int = 0) -> Tens
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> from redcat.utils.tensor import permute_along_dim
         >>> permute_along_dim(tensor=torch.arange(4), permutation=torch.tensor([0, 2, 1, 3]))
@@ -309,7 +309,7 @@ def swap2(
 
     Example usage:
 
-    .. code-block:: python
+    .. code-block:: pycon
 
         >>> from redcat.utils.tensor import swap2
         >>> seq = [1, 2, 3, 4, 5]