Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.3022. Min Act: -0.1700
Data Index: 2363785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.3022. Min Act: -0.1700
Data Index: 1851769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.3022. Min Act: -0.1700
Data Index: 449044 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2709. Min Act: -0.1700
Data Index: 2600578 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2709. Min Act: -0.1700
Data Index: 5519324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2709. Min Act: -0.1699
Data Index: 5131723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2709. Min Act: -0.1700
Data Index: 7968360 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 3705282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2084. Min Act: -0.1700
Data Index: 424558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 800066 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 4123934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2084. Min Act: -0.1700
Data Index: 3532174 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 1724392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 4804035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 3254668 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 1653861 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 5246910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 2044552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 6348123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3022. Min Range: -4.3022
Max Act: 4.2397. Min Act: -0.1700
Data Index: 1494158 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19