Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0466. Min Range: -7.0466
Max Act: 7.0466. Min Act: -0.1700
Data Index: 2066509 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.9528. Min Act: -0.1700
Data Index: 4392331 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.8903. Min Act: -0.1700
Data Index: 2601666 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.8591. Min Act: -0.1700
Data Index: 1680931 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.8278. Min Act: -0.1700
Data Index: 5086477 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7966. Min Act: -0.1700
Data Index: 5073582 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7966. Min Act: -0.1700
Data Index: 5944824 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7966. Min Act: -0.1700
Data Index: 3133679 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7028. Min Act: -0.1700
Data Index: 8295144 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7028. Min Act: -0.1700
Data Index: 5401703 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.7028. Min Act: -0.1700
Data Index: 3894004 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.6403. Min Act: -0.1700
Data Index: 2749091 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.5778. Min Act: -0.1700
Data Index: 5208468 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.6091. Min Act: -0.1700
Data Index: 6010392 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.6091. Min Act: -0.1700
Data Index: 5901064 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7646566 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.5778. Min Act: -0.1700
Data Index: 2289852 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.5778. Min Act: -0.1700
Data Index: 6602352 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.5153. Min Act: -0.1700
Data Index: 4491991 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0466. Min Range: -7.0466
Max Act: 6.5466. Min Act: -0.1700
Data Index: 1592324 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19