Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.9792. Min Act: -0.1700
Data Index: 4413247 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.8542. Min Act: -0.1700
Data Index: 3528592 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.7604. Min Act: -0.1700
Data Index: 7307479 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.7917. Min Act: -0.1700
Data Index: 3716149 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6979. Min Act: -0.1700
Data Index: 2614220 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.7292. Min Act: -0.1700
Data Index: 1549956 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.7917. Min Act: -0.1700
Data Index: 595495 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.7292. Min Act: -0.1700
Data Index: 4328062 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6667. Min Act: -0.1700
Data Index: 474795 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6667. Min Act: -0.1700
Data Index: 4121938 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6979. Min Act: -0.1700
Data Index: 1971065 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6354. Min Act: -0.1700
Data Index: 4650415 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6354. Min Act: -0.1700
Data Index: 6493057 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6667. Min Act: -0.1700
Data Index: 3478197 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6042. Min Act: -0.1700
Data Index: 3273885 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6667. Min Act: -0.1700
Data Index: 8033951 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6667. Min Act: -0.1700
Data Index: 2705240 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6042. Min Act: -0.1700
Data Index: 2173699 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6042. Min Act: -0.1700
Data Index: 3773667 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9792. Min Range: -4.9792
Max Act: 4.6042. Min Act: -0.1700
Data Index: 1726834 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19