Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 480 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2388730 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.1690. Min Act: -0.1700
Data Index: 6296593 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.0752. Min Act: -0.1700
Data Index: 349980 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.0752. Min Act: -0.1700
Data Index: 6992604 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.0127. Min Act: -0.1700
Data Index: 7206478 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.9815. Min Act: -0.1700
Data Index: 508067 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2315. Min Range: -7.2315
Max Act: 7.0127. Min Act: -0.1700
Data Index: 4471924 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.9502. Min Act: -0.1700
Data Index: 4563782 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5813920 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.9190. Min Act: -0.1700
Data Index: 7689206 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.9190. Min Act: -0.1700
Data Index: 3623102 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.8565. Min Act: -0.1700
Data Index: 1017444 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.8877. Min Act: -0.1700
Data Index: 4584505 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.8877. Min Act: -0.1700
Data Index: 2654663 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5977384 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.8252. Min Act: -0.1700
Data Index: 5251275 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.7627. Min Act: -0.1700
Data Index: 3214823 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.7627. Min Act: -0.1700
Data Index: 4628831 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.7002. Min Act: -0.1700
Data Index: 7287748 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2315. Min Range: -7.2315
Max Act: 6.7002. Min Act: -0.1700
Data Index: 8079102 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19