Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 470 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.1411. Min Act: -0.1700
Data Index: 5580167 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3591854 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1411. Min Range: -4.1411
Max Act: 4.0161. Min Act: -0.1700
Data Index: 3731295 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9848. Min Act: -0.1700
Data Index: 1625986 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9848. Min Act: -0.1700
Data Index: 1520366 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9848. Min Act: -0.1700
Data Index: 6786596 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9223. Min Act: -0.1700
Data Index: 4396336 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9379. Min Act: -0.1700
Data Index: 8200842 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9067. Min Act: -0.1700
Data Index: 5839233 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9223. Min Act: -0.1700
Data Index: 2674294 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8910. Min Act: -0.1700
Data Index: 7231451 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9067. Min Act: -0.1700
Data Index: 7994294 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9067. Min Act: -0.1700
Data Index: 2872659 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1596572 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8754. Min Act: -0.1700
Data Index: 1495976 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9067. Min Act: -0.1700
Data Index: 961462 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8910. Min Act: -0.1700
Data Index: 2997463 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8754. Min Act: -0.1700
Data Index: 3663135 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.9067. Min Act: -0.1700
Data Index: 3202858 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1411. Min Range: -4.1411
Max Act: 3.8597. Min Act: -0.1700
Data Index: 3101885 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19