Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.7415. Min Act: -0.1700
Data Index: 5920138 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.3978. Min Act: -0.1700
Data Index: 7401709 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.3040. Min Act: -0.1700
Data Index: 5067510 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0853. Min Act: -0.1700
Data Index: 2373795 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0540. Min Act: -0.1700
Data Index: 2607438 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0228. Min Act: -0.1700
Data Index: 5150403 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0228. Min Act: -0.1700
Data Index: 2183171 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0228. Min Act: -0.1700
Data Index: 2492080 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0228. Min Act: -0.1700
Data Index: 4971456 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.9915. Min Act: -0.1700
Data Index: 5832995 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7415. Min Range: -6.7415
Max Act: 6.0228. Min Act: -0.1700
Data Index: 6291248 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.9603. Min Act: -0.1700
Data Index: 4909515 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.9290. Min Act: -0.1700
Data Index: 638857 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.9603. Min Act: -0.1700
Data Index: 8381756 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8978. Min Act: -0.1700
Data Index: 3429956 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8978. Min Act: -0.1700
Data Index: 5739639 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8978. Min Act: -0.1700
Data Index: 653828 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8978. Min Act: -0.1700
Data Index: 5296017 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8665. Min Act: -0.1700
Data Index: 2939041 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7415. Min Range: -6.7415
Max Act: 5.8978. Min Act: -0.1700
Data Index: 763833 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19