Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.9851. Min Act: -0.1700
Data Index: 4121456 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.9226. Min Act: -0.1699
Data Index: 5603147 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.8601. Min Act: -0.1700
Data Index: 3478463 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.7351. Min Act: -0.1700
Data Index: 1558734 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.6726. Min Act: -0.1700
Data Index: 2028558 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.6101. Min Act: -0.1700
Data Index: 8153884 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.5476. Min Act: -0.1700
Data Index: 104901 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.5476. Min Act: -0.1700
Data Index: 4792210 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4851. Min Act: -0.1700
Data Index: 479178 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4851. Min Act: -0.1700
Data Index: 829489 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4851. Min Act: -0.1700
Data Index: 4076886 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4226. Min Act: -0.1700
Data Index: 5249506 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4226. Min Act: -0.1700
Data Index: 5373800 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.4226. Min Act: -0.1700
Data Index: 3649637 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.3601. Min Act: -0.1700
Data Index: 521469 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.3601. Min Act: -0.1700
Data Index: 4707640 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.3601. Min Act: -0.1700
Data Index: 1447504 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.3601. Min Act: -0.1700
Data Index: 6848846 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.2351. Min Act: -0.1699
Data Index: 3292092 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9851. Min Range: -9.9851
Max Act: 9.2976. Min Act: -0.1700
Data Index: 2603021 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19