Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.9242. Min Act: -0.1700
Data Index: 2637631 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.9242. Min Act: -0.1700
Data Index: 690782 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.7992. Min Act: -0.1700
Data Index: 670323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.7992. Min Act: -0.1700
Data Index: 7870397 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.7367. Min Act: -0.1700
Data Index: 3780200 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.7055. Min Act: -0.1700
Data Index: 8759091 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6430. Min Act: -0.1700
Data Index: 8069966 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6430. Min Act: -0.1700
Data Index: 8694465 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 6204750 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 4864840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 6123965 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 4125894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 5076391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 3712255 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.5805. Min Act: -0.1700
Data Index: 3608453 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 6204780 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 556040 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.6117. Min Act: -0.1700
Data Index: 6204723 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.5805. Min Act: -0.1700
Data Index: 7613549 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9242. Min Range: -4.9242
Max Act: 4.5805. Min Act: -0.1700
Data Index: 870007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19