Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3737. Min Range: -9.3737
Max Act: 9.3737. Min Act: -0.1700
Data Index: 1693864 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3737. Min Range: -9.3737
Max Act: 9.3112. Min Act: -0.1700
Data Index: 2936804 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3737. Min Range: -9.3737
Max Act: 9.1862. Min Act: -0.1700
Data Index: 1788667 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.9987. Min Act: -0.1700
Data Index: 5134324 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3737. Min Range: -9.3737
Max Act: 9.0612. Min Act: -0.1700
Data Index: 6810826 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.9362. Min Act: -0.1700
Data Index: 2694438 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.9362. Min Act: -0.1700
Data Index: 7320075 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.8112. Min Act: -0.1700
Data Index: 3494458 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 737128 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 1077910 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.7487. Min Act: -0.1700
Data Index: 7668535 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 1539629 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 7587431 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 5580385 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6862. Min Act: -0.1700
Data Index: 3831251 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6237. Min Act: -0.1700
Data Index: 3974437 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6237. Min Act: -0.1700
Data Index: 375825 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6237. Min Act: -0.1700
Data Index: 5518424 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6237. Min Act: -0.1700
Data Index: 5799118 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3737. Min Range: -9.3737
Max Act: 8.6237. Min Act: -0.1700
Data Index: 3626927 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19