Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.3719. Min Range: -14.3719
Max Act: 14.3719. Min Act: -0.1700
Data Index: 6551739 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.3719. Min Range: -14.3719
Max Act: 14.1844. Min Act: -0.1687
Data Index: 8739484 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.3719. Min Range: -14.3719
Max Act: 14.1219. Min Act: -0.1700
Data Index: 8739487 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.8094. Min Act: -0.1698
Data Index: 4247192 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.8094. Min Act: -0.1699
Data Index: 6551737 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.7469. Min Act: -0.1700
Data Index: 6942037 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.7469. Min Act: -0.1699
Data Index: 5454876 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.6844. Min Act: -0.1698
Data Index: 8739486 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.6219. Min Act: -0.1700
Data Index: 1861752 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.5594. Min Act: -0.1697
Data Index: 5752129 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.5594. Min Act: -0.1700
Data Index: 3630482 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.5594. Min Act: -0.1700
Data Index: 8658752 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.5594. Min Act: -0.1633
Data Index: 7771307 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.5594. Min Act: -0.1700
Data Index: 2754669 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4969. Min Act: -0.1694
Data Index: 191592 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4969. Min Act: -0.1700
Data Index: 8577146 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4969. Min Act: -0.1700
Data Index: 2912662 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4969. Min Act: -0.1687
Data Index: 3657944 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4344. Min Act: -0.1700
Data Index: 1245746 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.3719. Min Range: -14.3719
Max Act: 13.4969. Min Act: -0.1699
Data Index: 4188791 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19