Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.9928. Min Act: -0.1700
Data Index: 271189 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.8053. Min Act: -0.1700
Data Index: 5227130 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.7428. Min Act: -0.1700
Data Index: 7812341 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.6803. Min Act: -0.1700
Data Index: 5987092 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.6803. Min Act: -0.1700
Data Index: 2475206 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.6178. Min Act: -0.1700
Data Index: 1468628 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.5553. Min Act: -0.1700
Data Index: 1763403 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.5553. Min Act: -0.1700
Data Index: 4018766 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.4928. Min Act: -0.1700
Data Index: 1101428 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.5553. Min Act: -0.1700
Data Index: 7764665 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.5553. Min Act: -0.1700
Data Index: 5145475 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.4928. Min Act: -0.1700
Data Index: 16236 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.4928. Min Act: -0.1700
Data Index: 6212483 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.4303. Min Act: -0.1700
Data Index: 7665912 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.3678. Min Act: -0.1700
Data Index: 1717962 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.4303. Min Act: -0.1700
Data Index: 3957526 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.3678. Min Act: -0.1700
Data Index: 1128547 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.3678. Min Act: -0.1700
Data Index: 6806699 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.3678. Min Act: -0.1700
Data Index: 6429980 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9928. Min Range: -10.9928
Max Act: 10.3678. Min Act: -0.1700
Data Index: 3138485 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19