Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6078 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0796. Min Range: -5.0796
Max Act: 5.0796. Min Act: -0.1700
Data Index: 5175959 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0796. Min Range: -5.0796
Max Act: 5.0171. Min Act: -0.1700
Data Index: 6750954 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.9546. Min Act: -0.1700
Data Index: 1507808 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.8296. Min Act: -0.1700
Data Index: 5277425 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.8608. Min Act: -0.1700
Data Index: 7311142 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7983. Min Act: -0.1700
Data Index: 8341624 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7671. Min Act: -0.1700
Data Index: 4673444 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7671. Min Act: -0.1700
Data Index: 135054 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7358. Min Act: -0.1700
Data Index: 4084787 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7358. Min Act: -0.1700
Data Index: 2333022 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7046. Min Act: -0.1700
Data Index: 8692386 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.7358. Min Act: -0.1700
Data Index: 4688115 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3220044 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6733. Min Act: -0.1700
Data Index: 279898 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6421. Min Act: -0.1700
Data Index: 5590262 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6421. Min Act: -0.1700
Data Index: 2663105 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3139519 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6421. Min Act: -0.1700
Data Index: 3525349 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6421. Min Act: -0.1700
Data Index: 3051892 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0796. Min Range: -5.0796
Max Act: 4.6108. Min Act: -0.1700
Data Index: 948664 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19