Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3513. Min Range: -8.3513
Max Act: 8.3513. Min Act: -0.1700
Data Index: 3965535 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3513. Min Range: -8.3513
Max Act: 8.1326. Min Act: -0.1700
Data Index: 3459280 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3513. Min Range: -8.3513
Max Act: 8.0701. Min Act: -0.1700
Data Index: 5127858 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3513. Min Range: -8.3513
Max Act: 8.0076. Min Act: -0.1700
Data Index: 4259580 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3513. Min Range: -8.3513
Max Act: 8.0076. Min Act: -0.1700
Data Index: 2321701 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9763. Min Act: -0.1700
Data Index: 155937 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9451. Min Act: -0.1700
Data Index: 8156160 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9451. Min Act: -0.1700
Data Index: 7668060 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9451. Min Act: -0.1700
Data Index: 2930955 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9138. Min Act: -0.1700
Data Index: 5707576 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8826. Min Act: -0.1700
Data Index: 4948702 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9138. Min Act: -0.1700
Data Index: 6915614 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9138. Min Act: -0.1700
Data Index: 1528927 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8826. Min Act: -0.1700
Data Index: 1127966 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8826. Min Act: -0.1700
Data Index: 5870558 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.9138. Min Act: -0.1700
Data Index: 4727778 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8513. Min Act: -0.1700
Data Index: 8009733 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8201. Min Act: -0.1700
Data Index: 5988855 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8513. Min Act: -0.1700
Data Index: 5169056 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3513. Min Range: -8.3513
Max Act: 7.8513. Min Act: -0.1700
Data Index: 1365413 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19