Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.4509. Min Act: -0.1700
Data Index: 7692903 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.3254. Min Act: -0.1700
Data Index: 2189598 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.3254. Min Act: -0.1700
Data Index: 6428991 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.3254. Min Act: -0.1700
Data Index: 3839079 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.3254. Min Act: -0.1700
Data Index: 711677 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.3098. Min Act: -0.1700
Data Index: 4800593 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2626. Min Act: -0.1700
Data Index: 142714 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2626. Min Act: -0.1700
Data Index: 539952 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2312. Min Act: -0.1700
Data Index: 4059101 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 4507224 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 1834796 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2469. Min Act: -0.1700
Data Index: 4924406 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2469. Min Act: -0.1700
Data Index: 5531443 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2312. Min Act: -0.1700
Data Index: 607525 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2312. Min Act: -0.1700
Data Index: 837769 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2312. Min Act: -0.1700
Data Index: 3781496 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 5141553 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 2614295 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 3443301 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4509. Min Range: -3.4509
Max Act: 3.2155. Min Act: -0.1700
Data Index: 1914325 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19