Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.8386. Min Act: -0.1700
Data Index: 3937984 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.5573. Min Act: -0.1700
Data Index: 6201148 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.3698. Min Act: -0.1700
Data Index: 476345 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.3386. Min Act: -0.1700
Data Index: 6937776 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.3386. Min Act: -0.1700
Data Index: 8374 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.2761. Min Act: -0.1700
Data Index: 1310690 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.2761. Min Act: -0.1700
Data Index: 7653332 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.2761. Min Act: -0.1700
Data Index: 5199094 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.2448. Min Act: -0.1700
Data Index: 8809324 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1823. Min Act: -0.1700
Data Index: 5380828 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1823. Min Act: -0.1700
Data Index: 3595696 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1823. Min Act: -0.1700
Data Index: 3274727 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1823. Min Act: -0.1700
Data Index: 3595700 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1511. Min Act: -0.1700
Data Index: 1977873 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.1198. Min Act: -0.1700
Data Index: 7224711 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.0886. Min Act: -0.1700
Data Index: 2708935 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.0886. Min Act: -0.1700
Data Index: 8143329 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8386. Min Range: -6.8386
Max Act: 6.0573. Min Act: -0.1700
Data Index: 2359576 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8386. Min Range: -6.8386
Max Act: 5.9948. Min Act: -0.1700
Data Index: 6214169 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8386. Min Range: -6.8386
Max Act: 5.9948. Min Act: -0.1700
Data Index: 7097893 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19