Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2265 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.8531. Min Act: -0.1700
Data Index: 3320120 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.8219. Min Act: -0.1700
Data Index: 5768538 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.8219. Min Act: -0.1700
Data Index: 5616296 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.8219. Min Act: -0.1700
Data Index: 1144368 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.7906. Min Act: -0.1700
Data Index: 1908977 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.7906. Min Act: -0.1700
Data Index: 4442522 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.7281. Min Act: -0.1700
Data Index: 7109170 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.7281. Min Act: -0.1700
Data Index: 6285228 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.7281. Min Act: -0.1700
Data Index: 1042181 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6557704 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7148450 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6344. Min Act: -0.1700
Data Index: 2471629 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6344. Min Act: -0.1700
Data Index: 1862324 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6031. Min Act: -0.1700
Data Index: 3714617 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6031. Min Act: -0.1700
Data Index: 6015191 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6344. Min Act: -0.1700
Data Index: 1781409 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.6031. Min Act: -0.1700
Data Index: 5327343 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.5719. Min Act: -0.1700
Data Index: 1562479 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1300727 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8531. Min Range: -6.8531
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4709735 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19