Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6068 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.1315. Min Act: -0.1700
Data Index: 145788 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.1002. Min Act: -0.1700
Data Index: 5800763 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.0690. Min Act: -0.1700
Data Index: 1216901 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.0690. Min Act: -0.1700
Data Index: 7775997 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.0377. Min Act: -0.1700
Data Index: 126622 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1315. Min Range: -7.1315
Max Act: 7.0065. Min Act: -0.1700
Data Index: 6168265 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 1062634 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9752. Min Act: -0.1700
Data Index: 3402930 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9752. Min Act: -0.1700
Data Index: 2566907 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 7627264 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 6500783 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9127. Min Act: -0.1700
Data Index: 6168868 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.9440. Min Act: -0.1700
Data Index: 6168267 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6279350 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.8502. Min Act: -0.1700
Data Index: 4293456 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.8190. Min Act: -0.1700
Data Index: 4911078 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.7565. Min Act: -0.1700
Data Index: 553817 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.8190. Min Act: -0.1700
Data Index: 1291673 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.7877. Min Act: -0.1700
Data Index: 8038268 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1315. Min Range: -7.1315
Max Act: 6.7565. Min Act: -0.1700
Data Index: 8038267 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19