Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1150 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0535. Min Range: -4.0535
Max Act: 4.0535. Min Act: -0.1700
Data Index: 8765428 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0535. Min Range: -4.0535
Max Act: 4.0535. Min Act: -0.1700
Data Index: 951075 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0535. Min Range: -4.0535
Max Act: 4.0222. Min Act: -0.1700
Data Index: 8765425 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0535. Min Range: -4.0535
Max Act: 4.0535. Min Act: -0.1700
Data Index: 7202132 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.9597. Min Act: -0.1700
Data Index: 3749050 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.9910. Min Act: -0.1700
Data Index: 4169891 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 4002970 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.9284. Min Act: -0.1700
Data Index: 1078280 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 5849205 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 2625425 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 2813150 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 3543942 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8659. Min Act: -0.1700
Data Index: 709092 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 8055508 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8780558 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8659. Min Act: -0.1700
Data Index: 4033275 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8972. Min Act: -0.1700
Data Index: 4081359 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8346. Min Act: -0.1700
Data Index: 4169889 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8455233 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0535. Min Range: -4.0535
Max Act: 3.8346. Min Act: -0.1700
Data Index: 8289031 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19