Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2299. Min Range: -7.2299
Max Act: 7.2299. Min Act: -0.1700
Data Index: 7824440 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.9487. Min Act: -0.1700
Data Index: 6695778 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.8549. Min Act: -0.1700
Data Index: 709466 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.7612. Min Act: -0.1700
Data Index: 7925539 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.7299. Min Act: -0.1700
Data Index: 1167289 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6674. Min Act: -0.1700
Data Index: 3606859 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 7767251 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 7517474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 3757575 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 949218 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 4155216 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6362. Min Act: -0.1700
Data Index: 6766676 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 86124 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 7435153 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 304925 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 8194300 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.6049. Min Act: -0.1700
Data Index: 2698169 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.5737. Min Act: -0.1700
Data Index: 7016659 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.5737. Min Act: -0.1700
Data Index: 3917532 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2299. Min Range: -7.2299
Max Act: 6.5737. Min Act: -0.1700
Data Index: 3757572 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19