Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6156. Min Range: -9.6156
Max Act: 9.6156. Min Act: -0.1700
Data Index: 7757464 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6156. Min Range: -9.6156
Max Act: 9.1781. Min Act: -0.1700
Data Index: 6772217 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.9906. Min Act: -0.1700
Data Index: 3054966 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.9281. Min Act: -0.1700
Data Index: 600814 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.8031. Min Act: -0.1700
Data Index: 3019719 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.8656. Min Act: -0.1700
Data Index: 7745202 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.8031. Min Act: -0.1700
Data Index: 273331 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.6781. Min Act: -0.1700
Data Index: 4157832 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.6156. Min Act: -0.1700
Data Index: 1782657 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.6156. Min Act: -0.1700
Data Index: 852391 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.6156. Min Act: -0.1700
Data Index: 3327225 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.5531. Min Act: -0.1700
Data Index: 8232990 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.5531. Min Act: -0.1700
Data Index: 2724580 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.5531. Min Act: -0.1700
Data Index: 5520093 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.5531. Min Act: -0.1700
Data Index: 592027 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.4906. Min Act: -0.1700
Data Index: 7260475 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.4906. Min Act: -0.1700
Data Index: 8195305 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.4906. Min Act: -0.1700
Data Index: 5553019 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.4281. Min Act: -0.1700
Data Index: 5643469 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6156. Min Range: -9.6156
Max Act: 8.4281. Min Act: -0.1700
Data Index: 1854212 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19