Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 7059398 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7389. Min Act: -0.1700
Data Index: 7535493 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3340267 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3397903 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 3723555 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3723665 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6290769 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6139. Min Act: -0.1700
Data Index: 6166572 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5514. Min Act: -0.1700
Data Index: 1309409 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5514. Min Act: -0.1700
Data Index: 5046301 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5514. Min Act: -0.1700
Data Index: 6890845 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5514. Min Act: -0.1700
Data Index: 839250 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5202. Min Act: -0.1700
Data Index: 3233113 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.5202. Min Act: -0.1700
Data Index: 5809798 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4889. Min Act: -0.1700
Data Index: 747896 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4889. Min Act: -0.1700
Data Index: 3196842 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4889. Min Act: -0.1700
Data Index: 7759225 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4264. Min Act: -0.1700
Data Index: 4048937 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4577. Min Act: -0.1700
Data Index: 5973779 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.4577. Min Act: -0.1700
Data Index: 4991988 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19