Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5254 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1315. Min Range: -6.1315
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8640946 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1315. Min Range: -6.1315
Max Act: 6.0065. Min Act: -0.1700
Data Index: 4657614 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.9752. Min Act: -0.1700
Data Index: 2428067 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.9127. Min Act: -0.1700
Data Index: 8127471 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.8815. Min Act: -0.1700
Data Index: 2171185 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 3489458 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 1405993 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 7768014 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7877. Min Act: -0.1700
Data Index: 3697637 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7252. Min Act: -0.1700
Data Index: 2479752 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.7252. Min Act: -0.1700
Data Index: 4762470 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6940. Min Act: -0.1700
Data Index: 4541472 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 3843152 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 5839178 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 870516 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 6549801 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 980710 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 2293936 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6627. Min Act: -0.1700
Data Index: 6013397 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1315. Min Range: -6.1315
Max Act: 5.6315. Min Act: -0.1700
Data Index: 5333292 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19