Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4257747 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6917. Min Act: -0.1700
Data Index: 1970908 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6917. Min Act: -0.1700
Data Index: 5970220 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6604. Min Act: -0.1700
Data Index: 8064631 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6604. Min Act: -0.1700
Data Index: 6310429 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5749427 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 7622542 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 6513757 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8537135 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 476701 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 2550450 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 7660384 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.6292. Min Act: -0.1700
Data Index: 2386232 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 1592209 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 974473 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 3071842 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 8219242 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 3097424 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5979. Min Act: -0.1700
Data Index: 6917760 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.5667. Min Act: -0.1700
Data Index: 6323028 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19