Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.6274. Min Act: -0.1700
Data Index: 5619431 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.6118. Min Act: -0.1700
Data Index: 7879515 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.5648. Min Act: -0.1700
Data Index: 4211424 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.5492. Min Act: -0.1700
Data Index: 6730743 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.5335. Min Act: -0.1700
Data Index: 697614 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.5335. Min Act: -0.1700
Data Index: 3786802 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.5335. Min Act: -0.1700
Data Index: 5338467 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.4552. Min Act: -0.1700
Data Index: 2535754 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.4552. Min Act: -0.1700
Data Index: 8367489 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.4709. Min Act: -0.1700
Data Index: 5911737 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.4395. Min Act: -0.1700
Data Index: 4954968 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.4082. Min Act: -0.1700
Data Index: 5911738 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3768. Min Act: -0.1700
Data Index: 2535753 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3925. Min Act: -0.1700
Data Index: 628939 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3768. Min Act: -0.1700
Data Index: 657756 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3768. Min Act: -0.1700
Data Index: 3335466 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3611. Min Act: -0.1700
Data Index: 7057352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3768. Min Act: -0.1700
Data Index: 1230307 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3454. Min Act: -0.1700
Data Index: 628929 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6274. Min Range: -3.6274
Max Act: 3.3141. Min Act: -0.1700
Data Index: 5210832 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19