Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.7398. Min Act: -0.1700
Data Index: 4021454 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.7225. Min Act: -0.1700
Data Index: 8825336 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.7052. Min Act: -0.1700
Data Index: 7697880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.7052. Min Act: -0.1700
Data Index: 4054135 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6878. Min Act: -0.1700
Data Index: 1950450 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6878. Min Act: -0.1700
Data Index: 124915 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6704. Min Act: -0.1700
Data Index: 5210481 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6704. Min Act: -0.1700
Data Index: 4389572 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6704. Min Act: -0.1699
Data Index: 7569449 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6704. Min Act: -0.1700
Data Index: 7569446 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6704. Min Act: -0.1700
Data Index: 4540378 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6530. Min Act: -0.1700
Data Index: 8364862 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 2086514 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 7011626 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 6729025 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 6542096 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 858474 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 772683 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 6054461 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7398. Min Range: -1.7398
Max Act: 1.6356. Min Act: -0.1700
Data Index: 3047191 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19