Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.9091. Min Act: -0.1700
Data Index: 2728575 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.5966. Min Act: -0.1700
Data Index: 7620863 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.5654. Min Act: -0.1700
Data Index: 3222712 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.4404. Min Act: -0.1700
Data Index: 3917032 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.3154. Min Act: -0.1700
Data Index: 17003 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.3154. Min Act: -0.1700
Data Index: 6586788 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.2529. Min Act: -0.1700
Data Index: 7751254 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.2529. Min Act: -0.1700
Data Index: 7773939 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.2216. Min Act: -0.1700
Data Index: 2976233 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.2529. Min Act: -0.1700
Data Index: 1886688 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.1591. Min Act: -0.1700
Data Index: 2032815 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.1591. Min Act: -0.1700
Data Index: 1331068 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.1279. Min Act: -0.1700
Data Index: 2736814 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.1279. Min Act: -0.1700
Data Index: 7651857 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.1279. Min Act: -0.1700
Data Index: 3684081 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.0966. Min Act: -0.1700
Data Index: 3955916 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.0966. Min Act: -0.1700
Data Index: 296328 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.0966. Min Act: -0.1700
Data Index: 8827690 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.0966. Min Act: -0.1700
Data Index: 1723886 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9091. Min Range: -7.9091
Max Act: 7.0654. Min Act: -0.1700
Data Index: 267509 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19