Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 693 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2871. Min Range: -8.2871
Max Act: 8.2871. Min Act: -0.1700
Data Index: 3648903 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2871. Min Range: -8.2871
Max Act: 8.0996. Min Act: -0.1700
Data Index: 4332528 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.7871. Min Act: -0.1700
Data Index: 5358398 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.6934. Min Act: -0.1700
Data Index: 8094143 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.6309. Min Act: -0.1700
Data Index: 7033998 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.6309. Min Act: -0.1700
Data Index: 5520266 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.5371. Min Act: -0.1700
Data Index: 8338614 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.5371. Min Act: -0.1700
Data Index: 5817200 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.4746. Min Act: -0.1700
Data Index: 8556334 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.4746. Min Act: -0.1700
Data Index: 4702987 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.4746. Min Act: -0.1700
Data Index: 1114010 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.4121. Min Act: -0.1700
Data Index: 45888 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3809. Min Act: -0.1700
Data Index: 5008049 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3496. Min Act: -0.1700
Data Index: 6763364 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3809. Min Act: -0.1700
Data Index: 7731195 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3496. Min Act: -0.1700
Data Index: 3299732 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3184. Min Act: -0.1700
Data Index: 5304647 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3496. Min Act: -0.1700
Data Index: 2327212 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.3496. Min Act: -0.1700
Data Index: 303529 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2871. Min Range: -8.2871
Max Act: 7.2871. Min Act: -0.1700
Data Index: 7053428 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19