Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.8789. Min Act: -0.1700
Data Index: 8643313 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.3789. Min Act: -0.1700
Data Index: 533475 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.3164. Min Act: -0.1700
Data Index: 7774001 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.3164. Min Act: -0.1700
Data Index: 4791728 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.1289. Min Act: -0.1700
Data Index: 7779824 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8789. Min Range: -9.8789
Max Act: 9.0664. Min Act: -0.1700
Data Index: 1202772 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.9414. Min Act: -0.1700
Data Index: 5590410 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.8789. Min Act: -0.1700
Data Index: 5274278 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.8789. Min Act: -0.1700
Data Index: 6975914 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.8789. Min Act: -0.1700
Data Index: 3942173 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.8789. Min Act: -0.1700
Data Index: 8832819 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.8164. Min Act: -0.1700
Data Index: 5391039 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.7539. Min Act: -0.1700
Data Index: 3523338 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.7539. Min Act: -0.1700
Data Index: 3677550 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6914. Min Act: -0.1700
Data Index: 5448447 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6914. Min Act: -0.1700
Data Index: 5052334 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6914. Min Act: -0.1700
Data Index: 1873167 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6289. Min Act: -0.1700
Data Index: 1907643 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6289. Min Act: -0.1700
Data Index: 7975576 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8789. Min Range: -9.8789
Max Act: 8.6289. Min Act: -0.1700
Data Index: 3106286 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19