Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5495 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.9874. Min Act: -0.1700
Data Index: 1409640 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.6749. Min Act: -0.1700
Data Index: 4268541 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.5499. Min Act: -0.1700
Data Index: 2649767 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.5186. Min Act: -0.1700
Data Index: 2113387 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.5186. Min Act: -0.1700
Data Index: 6659853 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4874. Min Act: -0.1700
Data Index: 3137093 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4874. Min Act: -0.1700
Data Index: 2372820 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4874. Min Act: -0.1700
Data Index: 5461681 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4874. Min Act: -0.1700
Data Index: 6422893 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4561. Min Act: -0.1700
Data Index: 5121054 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.4249. Min Act: -0.1700
Data Index: 2977985 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3936. Min Act: -0.1700
Data Index: 8545847 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3936. Min Act: -0.1700
Data Index: 5257696 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 8770752 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 3030362 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 2421676 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 115545 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3936. Min Act: -0.1700
Data Index: 1867073 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 5257690 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9874. Min Range: -4.9874
Max Act: 4.3624. Min Act: -0.1700
Data Index: 6975295 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19