Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 492 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.5041. Min Act: -0.1700
Data Index: 8388958 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.3791. Min Act: -0.1700
Data Index: 3348656 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2853. Min Act: -0.1700
Data Index: 7853015 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2541. Min Act: -0.1700
Data Index: 7208199 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2228. Min Act: -0.1700
Data Index: 7209384 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1916. Min Act: -0.1700
Data Index: 3585912 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1603. Min Act: -0.1700
Data Index: 7911692 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1603. Min Act: -0.1700
Data Index: 5207855 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1291. Min Act: -0.1700
Data Index: 8399818 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1291. Min Act: -0.1700
Data Index: 5603681 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1291. Min Act: -0.1700
Data Index: 1739009 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6461904 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0978. Min Act: -0.1700
Data Index: 2157686 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0978. Min Act: -0.1700
Data Index: 4533570 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0978. Min Act: -0.1700
Data Index: 849977 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0978. Min Act: -0.1700
Data Index: 6172250 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0353. Min Act: -0.1700
Data Index: 1484914 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0666. Min Act: -0.1700
Data Index: 1279674 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0353. Min Act: -0.1700
Data Index: 513598 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.0353. Min Act: -0.1700
Data Index: 836767 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19