Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.2351. Min Act: -0.1700
Data Index: 6220664 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.2351. Min Act: -0.1700
Data Index: 836948 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1726. Min Act: -0.1700
Data Index: 6886727 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 7214811 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1726. Min Act: -0.1700
Data Index: 8648124 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1726. Min Act: -0.1700
Data Index: 3960562 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1726. Min Act: -0.1700
Data Index: 1707614 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1923197 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1864448 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1687429 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1545554 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.0476. Min Act: -0.1700
Data Index: 1298107 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1242119 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 227981 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1178749 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 224117 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 1046438 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 766652 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 688879 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2351. Min Range: -8.2351
Max Act: 8.1101. Min Act: -0.1700
Data Index: 160221 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19