Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.6379. Min Act: -0.1700
Data Index: 8512686 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.4504. Min Act: -0.1700
Data Index: 3272679 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.4191. Min Act: -0.1700
Data Index: 8420086 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.4504. Min Act: -0.1700
Data Index: 8007663 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.2941. Min Act: -0.1700
Data Index: 8624413 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.2941. Min Act: -0.1700
Data Index: 7564518 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.2316. Min Act: -0.1700
Data Index: 5692542 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.2629. Min Act: -0.1700
Data Index: 5842552 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.2316. Min Act: -0.1700
Data Index: 1862700 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1379. Min Act: -0.1700
Data Index: 210914 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 8663324 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1379. Min Act: -0.1700
Data Index: 4994463 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1379. Min Act: -0.1700
Data Index: 817668 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1066. Min Act: -0.1700
Data Index: 6783695 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1066. Min Act: -0.1700
Data Index: 6929144 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 7827815 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 7291815 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 62752 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.0754. Min Act: -0.1700
Data Index: 1765264 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6379. Min Range: -6.6379
Max Act: 6.1066. Min Act: -0.1700
Data Index: 7175181 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19