Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.9191. Min Act: -0.1700
Data Index: 347656 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.7316. Min Act: -0.1700
Data Index: 953295 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.7316. Min Act: -0.1700
Data Index: 8604425 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.7316. Min Act: -0.1700
Data Index: 4923525 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.7316. Min Act: -0.1700
Data Index: 1189456 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.5441. Min Act: -0.1700
Data Index: 961615 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.5441. Min Act: -0.1700
Data Index: 2744524 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.4816. Min Act: -0.1700
Data Index: 7567428 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.4816. Min Act: -0.1700
Data Index: 6322859 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.4191. Min Act: -0.1700
Data Index: 5799809 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.3566. Min Act: -0.1700
Data Index: 5905557 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.3566. Min Act: -0.1700
Data Index: 6208774 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.2941. Min Act: -0.1700
Data Index: 1229655 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.1691. Min Act: -0.1700
Data Index: 3761505 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.1691. Min Act: -0.1700
Data Index: 6135102 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.1066. Min Act: -0.1700
Data Index: 3280905 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.0441. Min Act: -0.1700
Data Index: 6655684 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.1066. Min Act: -0.1700
Data Index: 6545785 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.0441. Min Act: -0.1700
Data Index: 6317976 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9191. Min Range: -9.9191
Max Act: 9.0441. Min Act: -0.1700
Data Index: 4527508 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19