Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7311. Min Range: -9.7311
Max Act: 9.7311. Min Act: -0.1700
Data Index: 6711469 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7311. Min Range: -9.7311
Max Act: 9.4186. Min Act: -0.1700
Data Index: 6233664 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7311. Min Range: -9.7311
Max Act: 9.4811. Min Act: -0.1700
Data Index: 1640443 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7311. Min Range: -9.7311
Max Act: 9.4186. Min Act: -0.1700
Data Index: 7389239 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.8561. Min Act: -0.1700
Data Index: 8036190 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.8561. Min Act: -0.1700
Data Index: 7340370 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.7311. Min Act: -0.1700
Data Index: 3809990 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.6686. Min Act: -0.1700
Data Index: 3583558 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.6061. Min Act: -0.1700
Data Index: 5350223 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.6061. Min Act: -0.1700
Data Index: 593669 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.5436. Min Act: -0.1700
Data Index: 1163341 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.5436. Min Act: -0.1700
Data Index: 2104029 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4186. Min Act: -0.1700
Data Index: 3607506 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4811. Min Act: -0.1700
Data Index: 277981 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4186. Min Act: -0.1700
Data Index: 565018 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4186. Min Act: -0.1700
Data Index: 8650433 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.3561. Min Act: -0.1700
Data Index: 1108218 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4186. Min Act: -0.1700
Data Index: 4830506 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.4186. Min Act: -0.1700
Data Index: 7206549 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7311. Min Range: -9.7311
Max Act: 8.3561. Min Act: -0.1700
Data Index: 534808 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19