Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.8885. Min Act: -0.1700
Data Index: 3316207 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.8260. Min Act: -0.1700
Data Index: 6509824 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.7948. Min Act: -0.1700
Data Index: 2070348 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.7635. Min Act: -0.1700
Data Index: 2421245 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5186178 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.7010. Min Act: -0.1700
Data Index: 4787762 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.7010. Min Act: -0.1700
Data Index: 3508206 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6698. Min Act: -0.1700
Data Index: 1537303 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6698. Min Act: -0.1700
Data Index: 7911439 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6385. Min Act: -0.1700
Data Index: 1334289 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6385. Min Act: -0.1700
Data Index: 5660529 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6073. Min Act: -0.1700
Data Index: 6805331 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6073. Min Act: -0.1700
Data Index: 2725110 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6073. Min Act: -0.1700
Data Index: 3034059 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.5760. Min Act: -0.1700
Data Index: 8472876 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.5760. Min Act: -0.1700
Data Index: 8571427 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.5760. Min Act: -0.1700
Data Index: 2062537 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.5760. Min Act: -0.1700
Data Index: 685602 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.6073. Min Act: -0.1700
Data Index: 2097650 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8885. Min Range: -6.8885
Max Act: 6.5760. Min Act: -0.1700
Data Index: 3685507 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19