Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.8359. Min Act: -0.1700
Data Index: 2491832 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.8046. Min Act: -0.1700
Data Index: 2779086 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.8046. Min Act: -0.1700
Data Index: 7600948 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.7421. Min Act: -0.1700
Data Index: 3901671 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.7109. Min Act: -0.1700
Data Index: 2640580 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.7109. Min Act: -0.1700
Data Index: 8632927 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.6796. Min Act: -0.1700
Data Index: 3809066 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.5859. Min Act: -0.1700
Data Index: 4282283 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.6171. Min Act: -0.1700
Data Index: 6582904 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.5234. Min Act: -0.1700
Data Index: 975279 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.5234. Min Act: -0.1700
Data Index: 1584872 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.4609. Min Act: -0.1700
Data Index: 311099 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.4296. Min Act: -0.1700
Data Index: 6412430 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.4609. Min Act: -0.1700
Data Index: 1993098 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.4296. Min Act: -0.1700
Data Index: 4426460 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.3984. Min Act: -0.1700
Data Index: 6810919 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.3984. Min Act: -0.1700
Data Index: 5445222 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.3671. Min Act: -0.1700
Data Index: 3264030 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.3671. Min Act: -0.1700
Data Index: 2372247 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8359. Min Range: -7.8359
Max Act: 7.3359. Min Act: -0.1700
Data Index: 6717768 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19