Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 631 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0044. Min Range: -9.0044
Max Act: 9.0044. Min Act: -0.1700
Data Index: 5725604 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.6919. Min Act: -0.1700
Data Index: 741044 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.6919. Min Act: -0.1700
Data Index: 7656980 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.6294. Min Act: -0.1700
Data Index: 6386147 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.6294. Min Act: -0.1700
Data Index: 2326181 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.5669. Min Act: -0.1700
Data Index: 1398373 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.5044. Min Act: -0.1700
Data Index: 5163432 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.5044. Min Act: -0.1700
Data Index: 3722993 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.5044. Min Act: -0.1700
Data Index: 1109277 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.5044. Min Act: -0.1700
Data Index: 5642246 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.4419. Min Act: -0.1700
Data Index: 4596828 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.3794. Min Act: -0.1700
Data Index: 6563052 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.4419. Min Act: -0.1700
Data Index: 5530792 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.2544. Min Act: -0.1700
Data Index: 4154522 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.3169. Min Act: -0.1700
Data Index: 1925000 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.3169. Min Act: -0.1700
Data Index: 327311 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.2544. Min Act: -0.1700
Data Index: 7936723 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.3169. Min Act: -0.1700
Data Index: 5548554 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.3169. Min Act: -0.1700
Data Index: 3443961 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0044. Min Range: -9.0044
Max Act: 8.2544. Min Act: -0.1700
Data Index: 5612683 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19