Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.8861. Min Act: -0.1700
Data Index: 2892052 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7611. Min Act: -0.1700
Data Index: 8259289 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7611. Min Act: -0.1700
Data Index: 1889495 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 7509884 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 650769 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6986. Min Act: -0.1700
Data Index: 4552361 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.7299. Min Act: -0.1700
Data Index: 6970763 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6986. Min Act: -0.1700
Data Index: 636820 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 6631294 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 4860206 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 3882370 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 7197907 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 7695527 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 6642246 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6674. Min Act: -0.1700
Data Index: 2543550 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 7773041 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6361. Min Act: -0.1700
Data Index: 6222400 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.6049. Min Act: -0.1700
Data Index: 1750336 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.5736. Min Act: -0.1700
Data Index: 7603985 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8861. Min Range: -4.8861
Max Act: 4.5736. Min Act: -0.1700
Data Index: 2823830 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19