Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4573 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.7976. Min Act: -0.1700
Data Index: 5365311 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.7976. Min Act: -0.1700
Data Index: 3268637 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.7351. Min Act: -0.1700
Data Index: 525693 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6726. Min Act: -0.1700
Data Index: 1626090 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6726. Min Act: -0.1700
Data Index: 2047996 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6414. Min Act: -0.1700
Data Index: 399813 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6414. Min Act: -0.1700
Data Index: 1879694 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6101. Min Act: -0.1700
Data Index: 3079561 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6101. Min Act: -0.1700
Data Index: 6712096 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5789. Min Act: -0.1700
Data Index: 6362292 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.6101. Min Act: -0.1700
Data Index: 7063472 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5789. Min Act: -0.1700
Data Index: 6103211 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5476. Min Act: -0.1700
Data Index: 7744219 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5476. Min Act: -0.1700
Data Index: 4738423 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5476. Min Act: -0.1700
Data Index: 4874759 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5164. Min Act: -0.1700
Data Index: 5372111 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.5164. Min Act: -0.1700
Data Index: 7746525 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.4539. Min Act: -0.1700
Data Index: 7336427 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.4539. Min Act: -0.1700
Data Index: 223810 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7976. Min Range: -7.7976
Max Act: 7.4226. Min Act: -0.1700
Data Index: 957073 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19