Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1520 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.8268. Min Act: -0.1700
Data Index: 5842372 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.7631. Min Act: -0.1700
Data Index: 7531980 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6831. Min Act: -0.1700
Data Index: 5842366 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6831. Min Act: -0.1700
Data Index: 71667 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6350. Min Act: -0.1700
Data Index: 5842369 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6511. Min Act: -0.1700
Data Index: 3549730 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6350. Min Act: -0.1700
Data Index: 256815 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6350. Min Act: -0.1700
Data Index: 7016193 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6029. Min Act: -0.1700
Data Index: 6970412 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 1996681 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 364342 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 4229576 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 8095790 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 4168149 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.6029. Min Act: -0.1700
Data Index: 2797692 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5868. Min Act: -0.1700
Data Index: 6778775 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5707. Min Act: -0.1700
Data Index: 7253519 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5707. Min Act: -0.1700
Data Index: 6527436 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5707. Min Act: -0.1700
Data Index: 7016188 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8268. Min Range: -2.8268
Max Act: 2.5707. Min Act: -0.1700
Data Index: 396697 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19