Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2033 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0198. Min Range: -6.0198
Max Act: 6.0198. Min Act: -0.1700
Data Index: 4066388 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.8323. Min Act: -0.1700
Data Index: 6189613 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.8011. Min Act: -0.1700
Data Index: 8376962 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.7386. Min Act: -0.1700
Data Index: 6421847 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.5198. Min Act: -0.1700
Data Index: 7376137 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.4886. Min Act: -0.1700
Data Index: 7640885 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.4573. Min Act: -0.1700
Data Index: 1886749 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.4261. Min Act: -0.1700
Data Index: 5631238 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.4261. Min Act: -0.1700
Data Index: 6117562 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3948. Min Act: -0.1700
Data Index: 2658566 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3948. Min Act: -0.1700
Data Index: 1583425 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3948. Min Act: -0.1700
Data Index: 1669004 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3948. Min Act: -0.1700
Data Index: 6202845 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3636. Min Act: -0.1700
Data Index: 2947986 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3636. Min Act: -0.1700
Data Index: 3003656 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3323. Min Act: -0.1700
Data Index: 8354443 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3323. Min Act: -0.1700
Data Index: 1653060 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3323. Min Act: -0.1700
Data Index: 4937809 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3011. Min Act: -0.1700
Data Index: 2815020 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0198. Min Range: -6.0198
Max Act: 5.3011. Min Act: -0.1700
Data Index: 1081672 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19