Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2102. Min Range: -7.2102
Max Act: 7.2102. Min Act: -0.1700
Data Index: 5476732 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2102. Min Range: -7.2102
Max Act: 7.1164. Min Act: -0.1700
Data Index: 8712517 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2102. Min Range: -7.2102
Max Act: 7.0539. Min Act: -0.1700
Data Index: 1689079 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2102. Min Range: -7.2102
Max Act: 7.0227. Min Act: -0.1700
Data Index: 4058022 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2102. Min Range: -7.2102
Max Act: 7.0227. Min Act: -0.1700
Data Index: 3760755 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.9602. Min Act: -0.1700
Data Index: 2452794 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.9914. Min Act: -0.1700
Data Index: 6290661 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.8977. Min Act: -0.1700
Data Index: 4110573 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.8977. Min Act: -0.1700
Data Index: 8167533 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.8977. Min Act: -0.1700
Data Index: 2577087 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.8352. Min Act: -0.1700
Data Index: 4744069 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7727. Min Act: -0.1700
Data Index: 80131 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7727. Min Act: -0.1700
Data Index: 7470997 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7727. Min Act: -0.1700
Data Index: 628740 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7727. Min Act: -0.1700
Data Index: 8001868 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7727. Min Act: -0.1700
Data Index: 8418388 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7414. Min Act: -0.1700
Data Index: 1849627 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7102. Min Act: -0.1700
Data Index: 4845463 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7414. Min Act: -0.1700
Data Index: 7238709 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2102. Min Range: -7.2102
Max Act: 6.7414. Min Act: -0.1700
Data Index: 5448860 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19