Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.9936. Min Act: -0.1700
Data Index: 2613808 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.9311. Min Act: -0.1700
Data Index: 6039331 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.9311. Min Act: -0.1700
Data Index: 6470004 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.9311. Min Act: -0.1700
Data Index: 2203578 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.9311. Min Act: -0.1700
Data Index: 8655294 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8842. Min Act: -0.1700
Data Index: 5508152 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8686. Min Act: -0.1700
Data Index: 5508144 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8686. Min Act: -0.1700
Data Index: 660716 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8842. Min Act: -0.1700
Data Index: 432131 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8686. Min Act: -0.1700
Data Index: 8700386 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8529. Min Act: -0.1700
Data Index: 660715 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8373. Min Act: -0.1700
Data Index: 3292131 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8216. Min Act: -0.1700
Data Index: 4954708 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8373. Min Act: -0.1700
Data Index: 2063047 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8216. Min Act: -0.1700
Data Index: 1689593 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8373. Min Act: -0.1700
Data Index: 7957951 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8373. Min Act: -0.1700
Data Index: 7401690 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8216. Min Act: -0.1700
Data Index: 551292 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8216. Min Act: -0.1700
Data Index: 1185216 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9936. Min Range: -3.9936
Max Act: 3.8216. Min Act: -0.1700
Data Index: 8320825 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19