Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.3162. Min Act: -0.1700
Data Index: 5980519 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.2537. Min Act: -0.1700
Data Index: 5970850 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.1287. Min Act: -0.1700
Data Index: 3027784 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.1287. Min Act: -0.1700
Data Index: 5451820 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.0037. Min Act: -0.1700
Data Index: 2340548 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.0037. Min Act: -0.1700
Data Index: 139560 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3162. Min Range: -8.3162
Max Act: 8.0037. Min Act: -0.1700
Data Index: 2693565 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.9412. Min Act: -0.1700
Data Index: 4148009 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.9412. Min Act: -0.1700
Data Index: 8716601 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.8787. Min Act: -0.1700
Data Index: 4310549 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.9412. Min Act: -0.1700
Data Index: 497853 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.8162. Min Act: -0.1700
Data Index: 5262560 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.7537. Min Act: -0.1700
Data Index: 6325644 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.7537. Min Act: -0.1700
Data Index: 5259690 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.7537. Min Act: -0.1700
Data Index: 808987 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.7537. Min Act: -0.1700
Data Index: 6370882 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.6912. Min Act: -0.1700
Data Index: 8671126 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.6912. Min Act: -0.1700
Data Index: 6127554 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.6912. Min Act: -0.1700
Data Index: 5082520 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3162. Min Range: -8.3162
Max Act: 7.7537. Min Act: -0.1700
Data Index: 7682584 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19