Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.9435. Min Act: -0.1700
Data Index: 844923 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.8185. Min Act: -0.1700
Data Index: 6705800 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7560. Min Act: -0.1700
Data Index: 387248 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7560. Min Act: -0.1700
Data Index: 2969216 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4129097 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7560. Min Act: -0.1700
Data Index: 6701753 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7560. Min Act: -0.1700
Data Index: 5813738 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7247. Min Act: -0.1700
Data Index: 423197 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3611417 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6622. Min Act: -0.1700
Data Index: 7471309 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6935. Min Act: -0.1700
Data Index: 645 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6935. Min Act: -0.1700
Data Index: 718546 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6622. Min Act: -0.1700
Data Index: 8125446 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6310. Min Act: -0.1700
Data Index: 458721 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6622. Min Act: -0.1700
Data Index: 8682487 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6310. Min Act: -0.1700
Data Index: 400844 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6622. Min Act: -0.1700
Data Index: 5331699 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.5997. Min Act: -0.1700
Data Index: 2400263 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6310. Min Act: -0.1700
Data Index: 6838762 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9435. Min Range: -4.9435
Max Act: 4.6310. Min Act: -0.1700
Data Index: 7780479 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19