Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.7273. Min Act: -0.1700
Data Index: 469689 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.5398. Min Act: -0.1700
Data Index: 1108979 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.4148. Min Act: -0.1700
Data Index: 3676569 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.3210. Min Act: -0.1700
Data Index: 5957056 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.2585. Min Act: -0.1700
Data Index: 7418265 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.2273. Min Act: -0.1700
Data Index: 7187502 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.1648. Min Act: -0.1700
Data Index: 3418032 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.1648. Min Act: -0.1700
Data Index: 4236147 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.1335. Min Act: -0.1700
Data Index: 1868607 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.1335. Min Act: -0.1700
Data Index: 6175113 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.1023. Min Act: -0.1700
Data Index: 1385346 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0710. Min Act: -0.1700
Data Index: 3400320 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0710. Min Act: -0.1700
Data Index: 787505 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0398. Min Act: -0.1700
Data Index: 451527 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0398. Min Act: -0.1700
Data Index: 7839706 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0085. Min Act: -0.1700
Data Index: 1525273 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0085. Min Act: -0.1700
Data Index: 6371071 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0398. Min Act: -0.1700
Data Index: 2270553 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0398. Min Act: -0.1700
Data Index: 1283446 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7273. Min Range: -6.7273
Max Act: 6.0085. Min Act: -0.1700
Data Index: 7861767 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19