Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3801. Min Range: -8.3801
Max Act: 8.3801. Min Act: -0.1700
Data Index: 4094584 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.8176. Min Act: -0.1700
Data Index: 6924278 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.7551. Min Act: -0.1700
Data Index: 8146185 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.5989. Min Act: -0.1700
Data Index: 2479848 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4739. Min Act: -0.1700
Data Index: 3941769 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4739. Min Act: -0.1700
Data Index: 6471777 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4739. Min Act: -0.1700
Data Index: 5940378 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4114. Min Act: -0.1700
Data Index: 6833328 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4114. Min Act: -0.1700
Data Index: 2342305 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.4114. Min Act: -0.1700
Data Index: 3561175 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3801. Min Act: -0.1700
Data Index: 7744326 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3801. Min Act: -0.1700
Data Index: 779707 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3176. Min Act: -0.1700
Data Index: 7639158 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3176. Min Act: -0.1700
Data Index: 1808703 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3176. Min Act: -0.1700
Data Index: 1711368 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3176. Min Act: -0.1700
Data Index: 1955417 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.3176. Min Act: -0.1700
Data Index: 2538366 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.2551. Min Act: -0.1700
Data Index: 254160 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.2551. Min Act: -0.1700
Data Index: 1976151 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3801. Min Range: -8.3801
Max Act: 7.2239. Min Act: -0.1700
Data Index: 5930670 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19