Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7351. Min Act: -0.1700
Data Index: 1011817 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7039. Min Act: -0.1700
Data Index: 4615025 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6726. Min Act: -0.1700
Data Index: 7735732 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.7039. Min Act: -0.1700
Data Index: 5415566 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 576468 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6726. Min Act: -0.1700
Data Index: 2983801 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 1588629 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6414. Min Act: -0.1700
Data Index: 5194161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.6101. Min Act: -0.1700
Data Index: 531953 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4320009 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5789. Min Act: -0.1700
Data Index: 6845576 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 1640281 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 12151 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2284541 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 6863693 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 2882049 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 5059391 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 2593272 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 5439986 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7351. Min Range: -4.7351
Max Act: 4.5164. Min Act: -0.1700
Data Index: 1371695 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19