Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 885 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.5365. Min Act: -0.1700
Data Index: 5928278 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.2699. Min Act: -0.1700
Data Index: 2727105 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.2542. Min Act: -0.1700
Data Index: 547956 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.2071. Min Act: -0.1700
Data Index: 2888393 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.1756. Min Act: -0.1700
Data Index: 189998 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.1599. Min Act: -0.1700
Data Index: 6331517 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.1284. Min Act: -0.1700
Data Index: 6368311 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.1126. Min Act: -0.1700
Data Index: 692935 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.1126. Min Act: -0.1700
Data Index: 975947 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0811. Min Act: -0.1700
Data Index: 1593640 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0811. Min Act: -0.1700
Data Index: 1837064 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0654. Min Act: -0.1700
Data Index: 6331518 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0654. Min Act: -0.1700
Data Index: 299876 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0496. Min Act: -0.1700
Data Index: 5959723 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0496. Min Act: -0.1700
Data Index: 5902999 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0180. Min Act: -0.1700
Data Index: 626585 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0338. Min Act: -0.1700
Data Index: 4079072 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0496. Min Act: -0.1700
Data Index: 4461029 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0338. Min Act: -0.1700
Data Index: 2240663 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5365. Min Range: -3.5365
Max Act: 3.0338. Min Act: -0.1700
Data Index: 6996828 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19