Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 365 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0341. Min Range: -5.0341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 573191 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0341. Min Range: -5.0341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 6107953 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9404. Min Act: -0.1700
Data Index: 8458611 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9716. Min Act: -0.1700
Data Index: 8386122 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9404. Min Act: -0.1700
Data Index: 8768094 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9404. Min Act: -0.1700
Data Index: 3944533 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9404. Min Act: -0.1700
Data Index: 5541518 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9404. Min Act: -0.1700
Data Index: 4887818 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9716. Min Act: -0.1700
Data Index: 5696670 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.9091. Min Act: -0.1700
Data Index: 315494 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8779. Min Act: -0.1700
Data Index: 6018660 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8154. Min Act: -0.1700
Data Index: 5855849 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8466. Min Act: -0.1700
Data Index: 7658784 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8154. Min Act: -0.1700
Data Index: 6286374 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8154. Min Act: -0.1700
Data Index: 2737740 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.8466. Min Act: -0.1700
Data Index: 3361321 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.7529. Min Act: -0.1700
Data Index: 7203384 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.7841. Min Act: -0.1700
Data Index: 2849670 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.7529. Min Act: -0.1700
Data Index: 642405 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.7216. Min Act: -0.1700
Data Index: 5043978 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19