Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.4880. Min Act: -0.1700
Data Index: 7994688 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.4880. Min Act: -0.1700
Data Index: 2984946 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.4255. Min Act: -0.1700
Data Index: 196013 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.3005. Min Act: -0.1700
Data Index: 6117 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.3005. Min Act: -0.1700
Data Index: 859588 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.3318. Min Act: -0.1700
Data Index: 8623832 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.2380. Min Act: -0.1700
Data Index: 1365868 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1755. Min Act: -0.1700
Data Index: 3094007 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1443. Min Act: -0.1700
Data Index: 7725384 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.0193. Min Act: -0.1700
Data Index: 3142655 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 1119422 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 6277814 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 6573866 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 7963461 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9568. Min Act: -0.1700
Data Index: 3119112 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9255. Min Act: -0.1700
Data Index: 2582099 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8943. Min Act: -0.1700
Data Index: 6130730 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8630. Min Act: -0.1700
Data Index: 5417543 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8943. Min Act: -0.1700
Data Index: 7203878 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8630. Min Act: -0.1700
Data Index: 4139775 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19