Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1966. Min Range: -7.1966
Max Act: 7.1966. Min Act: -0.1700
Data Index: 3445247 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1966. Min Range: -7.1966
Max Act: 7.0403. Min Act: -0.1700
Data Index: 1847611 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.8528. Min Act: -0.1700
Data Index: 7856159 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.8216. Min Act: -0.1700
Data Index: 3929143 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.8216. Min Act: -0.1700
Data Index: 6525445 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.7278. Min Act: -0.1700
Data Index: 1305033 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.7278. Min Act: -0.1700
Data Index: 7619748 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.7278. Min Act: -0.1700
Data Index: 6319136 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.7278. Min Act: -0.1700
Data Index: 7960373 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.6966. Min Act: -0.1700
Data Index: 8701551 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.6653. Min Act: -0.1700
Data Index: 2025025 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.6653. Min Act: -0.1700
Data Index: 3268963 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.6028. Min Act: -0.1700
Data Index: 1879585 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5716. Min Act: -0.1700
Data Index: 3197332 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5403. Min Act: -0.1700
Data Index: 6303759 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 460448 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 4112379 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 8532200 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.5091. Min Act: -0.1700
Data Index: 4363713 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1966. Min Range: -7.1966
Max Act: 6.4778. Min Act: -0.1700
Data Index: 2655714 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19