Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5029 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0473. Min Range: -4.0473
Max Act: 4.0473. Min Act: -0.1700
Data Index: 5221967 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0473. Min Range: -4.0473
Max Act: 4.0160. Min Act: -0.1700
Data Index: 265202 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9847. Min Act: -0.1700
Data Index: 2889562 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0473. Min Range: -4.0473
Max Act: 4.0160. Min Act: -0.1700
Data Index: 5055468 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9847. Min Act: -0.1700
Data Index: 4929315 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9535. Min Act: -0.1700
Data Index: 8617319 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9535. Min Act: -0.1700
Data Index: 4260459 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9535. Min Act: -0.1700
Data Index: 5188509 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9535. Min Act: -0.1700
Data Index: 8787534 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 1407493 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 2782449 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 1407495 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 6379378 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 4185347 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.8909. Min Act: -0.1700
Data Index: 2672696 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.8909. Min Act: -0.1700
Data Index: 5243815 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.9222. Min Act: -0.1700
Data Index: 2045662 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.8909. Min Act: -0.1700
Data Index: 1525169 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.8597. Min Act: -0.1700
Data Index: 5114979 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0473. Min Range: -4.0473
Max Act: 3.8597. Min Act: -0.1700
Data Index: 2942241 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19