Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.9757. Min Act: -0.1700
Data Index: 4035555 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.9757. Min Act: -0.1700
Data Index: 3960754 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.8507. Min Act: -0.1700
Data Index: 2641220 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.8507. Min Act: -0.1700
Data Index: 6914625 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.8507. Min Act: -0.1700
Data Index: 1310131 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.8507. Min Act: -0.1700
Data Index: 8000338 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.7257. Min Act: -0.1700
Data Index: 1419113 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 4178700 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.7257. Min Act: -0.1700
Data Index: 1039785 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.7257. Min Act: -0.1700
Data Index: 6019515 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 1249178 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 3904820 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 3795732 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 8707428 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 1333380 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 1976980 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 7330835 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 1058005 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 5537427 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.9757. Min Range: -16.9757
Max Act: 16.6007. Min Act: -0.1700
Data Index: 2412558 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19