Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5937 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.9098. Min Act: -0.1700
Data Index: 7803641 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.7535. Min Act: -0.1700
Data Index: 6271935 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.6910. Min Act: -0.1700
Data Index: 6434376 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.5348. Min Act: -0.1700
Data Index: 6625748 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.5035. Min Act: -0.1700
Data Index: 8534154 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.5035. Min Act: -0.1700
Data Index: 8014984 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.4723. Min Act: -0.1700
Data Index: 5088594 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.5035. Min Act: -0.1700
Data Index: 2471760 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.4098. Min Act: -0.1700
Data Index: 4004188 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.3785. Min Act: -0.1700
Data Index: 7102467 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.3473. Min Act: -0.1700
Data Index: 4512211 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.3160. Min Act: -0.1700
Data Index: 3760877 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1586900 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.2535. Min Act: -0.1700
Data Index: 73308 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1156060 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.2223. Min Act: -0.1700
Data Index: 1187547 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.2223. Min Act: -0.1700
Data Index: 1313184 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.1910. Min Act: -0.1700
Data Index: 2758552 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5896740 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9098. Min Range: -5.9098
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7802994 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19