Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2173 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6791. Min Act: -0.1698
Data Index: 256584 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6791. Min Act: -0.1696
Data Index: 6345765 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6704. Min Act: -0.1695
Data Index: 3072809 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6791. Min Act: -0.1700
Data Index: 3802064 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6704. Min Act: -0.1700
Data Index: 3165094 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6704. Min Act: -0.1700
Data Index: 5998424 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6617. Min Act: -0.1700
Data Index: 3802074 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6443. Min Act: -0.1694
Data Index: 4580786 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6443. Min Act: -0.1696
Data Index: 8413944 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6443. Min Act: -0.1693
Data Index: 1017039 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6443. Min Act: -0.1699
Data Index: 4637462 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1699
Data Index: 4283600 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6269. Min Act: -0.1700
Data Index: 3556600 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1700
Data Index: 6130929 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1699
Data Index: 3802073 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1700
Data Index: 3823029 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1694
Data Index: 4033156 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6356. Min Act: -0.1695
Data Index: 7370933 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6269. Min Act: -0.1700
Data Index: 6361237 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6791. Min Range: -1.6791
Max Act: 1.6269. Min Act: -0.1690
Data Index: 3263451 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19