Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2358. Min Range: -9.2358
Max Act: 9.2358. Min Act: -0.1700
Data Index: 2097849 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2358. Min Range: -9.2358
Max Act: 9.1733. Min Act: -0.1700
Data Index: 7747135 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2358. Min Range: -9.2358
Max Act: 9.1108. Min Act: -0.1700
Data Index: 1251665 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2358. Min Range: -9.2358
Max Act: 9.1108. Min Act: -0.1700
Data Index: 5517062 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.9858. Min Act: -0.1700
Data Index: 8651661 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.9233. Min Act: -0.1700
Data Index: 4671058 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.8608. Min Act: -0.1700
Data Index: 270580 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.8608. Min Act: -0.1700
Data Index: 7972228 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7983. Min Act: -0.1700
Data Index: 5521657 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.8608. Min Act: -0.1700
Data Index: 931198 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.8608. Min Act: -0.1700
Data Index: 891843 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7983. Min Act: -0.1700
Data Index: 7200519 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7983. Min Act: -0.1700
Data Index: 1034389 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7983. Min Act: -0.1700
Data Index: 5046258 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7983. Min Act: -0.1700
Data Index: 5398569 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7358. Min Act: -0.1700
Data Index: 3504467 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7358. Min Act: -0.1700
Data Index: 7358121 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7358. Min Act: -0.1700
Data Index: 4094170 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7358. Min Act: -0.1700
Data Index: 6230457 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2358. Min Range: -9.2358
Max Act: 8.7358. Min Act: -0.1700
Data Index: 6665203 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19