Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2469. Min Range: -9.2469
Max Act: 9.2469. Min Act: -0.1700
Data Index: 873356 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2469. Min Range: -9.2469
Max Act: 9.1219. Min Act: -0.1699
Data Index: 4430029 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2469. Min Range: -9.2469
Max Act: 9.0594. Min Act: -0.1700
Data Index: 3248134 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.9969. Min Act: -0.1700
Data Index: 2383383 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 972788 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 7064854 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.8094. Min Act: -0.1700
Data Index: 333585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6844. Min Act: -0.1700
Data Index: 5601416 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 3325137 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6844. Min Act: -0.1698
Data Index: 8747858 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6844. Min Act: -0.1700
Data Index: 3960137 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6844. Min Act: -0.1700
Data Index: 2468329 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.7469. Min Act: -0.1700
Data Index: 990729 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6844. Min Act: -0.1700
Data Index: 899039 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 3177609 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.5594. Min Act: -0.1700
Data Index: 8303628 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 3824903 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 5983718 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 1967522 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2469. Min Range: -9.2469
Max Act: 8.6219. Min Act: -0.1700
Data Index: 4414043 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19