Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 2558063 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 3824487 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 1679904 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.4458. Min Act: -0.1700
Data Index: 7641242 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.3833. Min Act: -0.1700
Data Index: 1894198 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.3833. Min Act: -0.1700
Data Index: 5799125 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.3520. Min Act: -0.1700
Data Index: 216781 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.2895. Min Act: -0.1700
Data Index: 191909 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.2583. Min Act: -0.1700
Data Index: 259493 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.2270. Min Act: -0.1700
Data Index: 340127 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1958. Min Act: -0.1700
Data Index: 3754264 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1958. Min Act: -0.1700
Data Index: 7405048 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1958. Min Act: -0.1700
Data Index: 4073393 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1333. Min Act: -0.1700
Data Index: 6088934 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1333. Min Act: -0.1700
Data Index: 2197089 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1333. Min Act: -0.1700
Data Index: 5464454 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1020. Min Act: -0.1700
Data Index: 526695 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3040756 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1020. Min Act: -0.1700
Data Index: 3120614 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5395. Min Range: -6.5395
Max Act: 6.1333. Min Act: -0.1700
Data Index: 777455 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19