Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.8200. Min Act: -0.1700
Data Index: 8035517 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7563. Min Act: -0.1700
Data Index: 6700470 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7403. Min Act: -0.1700
Data Index: 344579 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7243. Min Act: -0.1700
Data Index: 6665699 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7403. Min Act: -0.1700
Data Index: 7036469 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7243. Min Act: -0.1700
Data Index: 4647941 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7243. Min Act: -0.1700
Data Index: 2551896 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7083. Min Act: -0.1700
Data Index: 876255 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6923. Min Act: -0.1700
Data Index: 1486386 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.7083. Min Act: -0.1700
Data Index: 1895723 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6923. Min Act: -0.1700
Data Index: 4541251 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6923. Min Act: -0.1700
Data Index: 1362405 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6763. Min Act: -0.1700
Data Index: 3710379 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6763. Min Act: -0.1700
Data Index: 4314454 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6603. Min Act: -0.1700
Data Index: 5301714 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6763. Min Act: -0.1700
Data Index: 7143577 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6603. Min Act: -0.1700
Data Index: 1906858 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6763. Min Act: -0.1700
Data Index: 4808849 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6442. Min Act: -0.1700
Data Index: 6276726 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8200. Min Range: -2.8200
Max Act: 2.6442. Min Act: -0.1700
Data Index: 3115540 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19