Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.7848. Min Act: -0.1700
Data Index: 6195699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.6598. Min Act: -0.1700
Data Index: 1386648 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1700
Data Index: 691097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1697
Data Index: 1363410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1700
Data Index: 6058905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1699
Data Index: 5764350 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1700
Data Index: 5348003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1700
Data Index: 2539947 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5973. Min Act: -0.1700
Data Index: 1689643 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5348. Min Act: -0.1700
Data Index: 2692523 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5660. Min Act: -0.1700
Data Index: 3239946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5660. Min Act: -0.1700
Data Index: 5273016 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5660. Min Act: -0.1700
Data Index: 7231365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5035. Min Act: -0.1700
Data Index: 617204 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5035. Min Act: -0.1700
Data Index: 4878146 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5348. Min Act: -0.1697
Data Index: 7923207 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5348. Min Act: -0.1700
Data Index: 4911854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5660. Min Act: -0.1696
Data Index: 4522715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5035. Min Act: -0.1700
Data Index: 814165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7848. Min Range: -4.7848
Max Act: 4.5035. Min Act: -0.1700
Data Index: 1349871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19