Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8177. Min Range: -8.8177
Max Act: 8.8177. Min Act: -0.1700
Data Index: 1348858 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8177. Min Range: -8.8177
Max Act: 8.3177. Min Act: -0.1700
Data Index: 8295873 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8177. Min Range: -8.8177
Max Act: 8.1302. Min Act: -0.1700
Data Index: 227736 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8177. Min Range: -8.8177
Max Act: 8.1302. Min Act: -0.1700
Data Index: 7279135 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8177. Min Range: -8.8177
Max Act: 8.0052. Min Act: -0.1700
Data Index: 6881381 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 8417955 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 3522415 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 3268659 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 8461334 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 2110870 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.9427. Min Act: -0.1700
Data Index: 5996601 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8802. Min Act: -0.1700
Data Index: 963540 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8802. Min Act: -0.1700
Data Index: 6756009 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8802. Min Act: -0.1700
Data Index: 1950867 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8802. Min Act: -0.1700
Data Index: 6758735 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8802. Min Act: -0.1700
Data Index: 6411364 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8177. Min Act: -0.1700
Data Index: 3260976 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8177. Min Act: -0.1700
Data Index: 7944991 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8177. Min Act: -0.1700
Data Index: 5104474 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8177. Min Range: -8.8177
Max Act: 7.8177. Min Act: -0.1700
Data Index: 8527336 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19