Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1282. Min Range: -12.1282
Max Act: 12.1282. Min Act: -0.1700
Data Index: 3472495 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1282. Min Range: -12.1282
Max Act: 12.0032. Min Act: -0.1700
Data Index: 6690815 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.9407. Min Act: -0.1700
Data Index: 1921017 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.9407. Min Act: -0.1700
Data Index: 2369914 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.7532. Min Act: -0.1700
Data Index: 3742097 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.8157. Min Act: -0.1700
Data Index: 3726261 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.7532. Min Act: -0.1700
Data Index: 3265113 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.6907. Min Act: -0.1700
Data Index: 2615971 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5657. Min Act: -0.1700
Data Index: 4534390 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5657. Min Act: -0.1700
Data Index: 1472765 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5657. Min Act: -0.1700
Data Index: 436477 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5032. Min Act: -0.1700
Data Index: 3452731 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5032. Min Act: -0.1700
Data Index: 3123344 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5032. Min Act: -0.1700
Data Index: 3871585 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.5032. Min Act: -0.1700
Data Index: 200216 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.4407. Min Act: -0.1700
Data Index: 1511619 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.4407. Min Act: -0.1700
Data Index: 138282 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.3782. Min Act: -0.1700
Data Index: 1295002 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.3782. Min Act: -0.1700
Data Index: 2753700 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1282. Min Range: -12.1282
Max Act: 11.3782. Min Act: -0.1700
Data Index: 5617462 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19