Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3871. Min Range: -7.3871
Max Act: 7.3871. Min Act: -0.1700
Data Index: 3900367 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.8871. Min Act: -0.1700
Data Index: 3714719 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.7621. Min Act: -0.1700
Data Index: 4327327 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.7621. Min Act: -0.1700
Data Index: 2756487 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.7308. Min Act: -0.1700
Data Index: 7380404 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.7621. Min Act: -0.1700
Data Index: 8539582 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6683. Min Act: -0.1700
Data Index: 2419352 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6996. Min Act: -0.1700
Data Index: 6967873 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6683. Min Act: -0.1700
Data Index: 722967 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6683. Min Act: -0.1700
Data Index: 8646513 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6371. Min Act: -0.1700
Data Index: 2582635 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6683. Min Act: -0.1700
Data Index: 2025994 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6058. Min Act: -0.1700
Data Index: 848104 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6058. Min Act: -0.1700
Data Index: 7628932 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6371. Min Act: -0.1700
Data Index: 7503620 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.6058. Min Act: -0.1700
Data Index: 5647865 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.5746. Min Act: -0.1700
Data Index: 2787422 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.5746. Min Act: -0.1700
Data Index: 6541830 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.5746. Min Act: -0.1700
Data Index: 1050033 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3871. Min Range: -7.3871
Max Act: 6.5746. Min Act: -0.1700
Data Index: 8625736 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19