Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.6684. Min Act: -0.1700
Data Index: 2308077 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.3559. Min Act: -0.1700
Data Index: 3928559 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.3559. Min Act: -0.1700
Data Index: 5486895 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.3559. Min Act: -0.1700
Data Index: 7904073 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.3559. Min Act: -0.1700
Data Index: 643309 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.2309. Min Act: -0.1700
Data Index: 3030343 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1684. Min Act: -0.1700
Data Index: 2863262 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.2309. Min Act: -0.1700
Data Index: 6597393 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.2309. Min Act: -0.1700
Data Index: 3913743 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1684. Min Act: -0.1700
Data Index: 1955350 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1684. Min Act: -0.1700
Data Index: 8479269 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1684. Min Act: -0.1700
Data Index: 1203166 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1684. Min Act: -0.1700
Data Index: 4554184 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.0434. Min Act: -0.1700
Data Index: 6121172 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1059. Min Act: -0.1700
Data Index: 2267436 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1059. Min Act: -0.1700
Data Index: 5011602 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.1059. Min Act: -0.1700
Data Index: 7469324 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.0434. Min Act: -0.1700
Data Index: 8106912 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.0434. Min Act: -0.1700
Data Index: 3872822 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6684. Min Range: -8.6684
Max Act: 8.0434. Min Act: -0.1700
Data Index: 853107 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19