Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.9333. Min Act: -0.1700
Data Index: 4216791 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.8395. Min Act: -0.1700
Data Index: 642581 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.8395. Min Act: -0.1700
Data Index: 3384108 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.8083. Min Act: -0.1700
Data Index: 1012468 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.6208. Min Act: -0.1700
Data Index: 2090887 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5895. Min Act: -0.1700
Data Index: 21603 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5895. Min Act: -0.1700
Data Index: 1170547 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5583. Min Act: -0.1700
Data Index: 270235 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.5270. Min Act: -0.1700
Data Index: 3274468 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 6575353 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4958. Min Act: -0.1700
Data Index: 2561754 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4645. Min Act: -0.1700
Data Index: 7234979 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4020. Min Act: -0.1700
Data Index: 8171998 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4020. Min Act: -0.1700
Data Index: 2633948 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4020. Min Act: -0.1700
Data Index: 1599244 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4020. Min Act: -0.1700
Data Index: 4062554 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.4333. Min Act: -0.1700
Data Index: 6832260 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.3708. Min Act: -0.1700
Data Index: 3625256 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.3708. Min Act: -0.1700
Data Index: 1914393 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9333. Min Range: -6.9333
Max Act: 6.3708. Min Act: -0.1700
Data Index: 1139412 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19