Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.9192. Min Act: -0.1700
Data Index: 1137816 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.4817. Min Act: -0.1700
Data Index: 404586 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.4192. Min Act: -0.1700
Data Index: 5582413 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.2942. Min Act: -0.1700
Data Index: 7237053 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.2317. Min Act: -0.1700
Data Index: 1604933 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.2004. Min Act: -0.1700
Data Index: 3271739 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.1692. Min Act: -0.1700
Data Index: 4515734 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.1379. Min Act: -0.1700
Data Index: 8089839 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.1067. Min Act: -0.1700
Data Index: 4939717 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.0442. Min Act: -0.1700
Data Index: 587732 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.0442. Min Act: -0.1700
Data Index: 3553726 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9192. Min Range: -7.9192
Max Act: 7.0129. Min Act: -0.1700
Data Index: 8775043 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.9504. Min Act: -0.1700
Data Index: 6045667 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.9192. Min Act: -0.1700
Data Index: 2944826 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.9192. Min Act: -0.1700
Data Index: 7554859 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.9504. Min Act: -0.1700
Data Index: 3396585 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.8879. Min Act: -0.1700
Data Index: 7898098 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.8879. Min Act: -0.1700
Data Index: 4976272 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.8879. Min Act: -0.1700
Data Index: 5973733 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9192. Min Range: -7.9192
Max Act: 6.8567. Min Act: -0.1700
Data Index: 5299378 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19