Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2821. Min Range: -8.2821
Max Act: 8.2821. Min Act: -0.1700
Data Index: 4212192 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.9071. Min Act: -0.1700
Data Index: 2362614 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.7821. Min Act: -0.1700
Data Index: 7076033 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.7821. Min Act: -0.1700
Data Index: 5600613 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.6571. Min Act: -0.1700
Data Index: 989375 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.6571. Min Act: -0.1700
Data Index: 629047 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5946. Min Act: -0.1700
Data Index: 1873970 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.6258. Min Act: -0.1700
Data Index: 793589 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5633. Min Act: -0.1700
Data Index: 1027773 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5946. Min Act: -0.1700
Data Index: 6648893 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5946. Min Act: -0.1700
Data Index: 6080901 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5633. Min Act: -0.1700
Data Index: 4207010 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5946. Min Act: -0.1700
Data Index: 7064080 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.5321. Min Act: -0.1700
Data Index: 5877790 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.4383. Min Act: -0.1700
Data Index: 1234505 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.4071. Min Act: -0.1700
Data Index: 4073934 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 2066966 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 4330997 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.3758. Min Act: -0.1700
Data Index: 1975766 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2821. Min Range: -8.2821
Max Act: 7.3446. Min Act: -0.1700
Data Index: 5887704 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19