Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0718. Min Range: -5.0718
Max Act: 5.0718. Min Act: -0.1700
Data Index: 6416160 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0718. Min Range: -5.0718
Max Act: 5.0093. Min Act: -0.1700
Data Index: 6856171 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.9155. Min Act: -0.1700
Data Index: 5448145 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.9155. Min Act: -0.1700
Data Index: 8829090 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.8218. Min Act: -0.1700
Data Index: 1855868 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.8218. Min Act: -0.1700
Data Index: 6334783 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7593. Min Act: -0.1700
Data Index: 2036085 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7905. Min Act: -0.1700
Data Index: 5562193 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7905. Min Act: -0.1700
Data Index: 3894261 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7593. Min Act: -0.1700
Data Index: 3616069 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7593. Min Act: -0.1700
Data Index: 5082828 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7905. Min Act: -0.1700
Data Index: 6176998 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7280. Min Act: -0.1700
Data Index: 1059869 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.7280. Min Act: -0.1700
Data Index: 5747876 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6968. Min Act: -0.1700
Data Index: 2800511 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6968. Min Act: -0.1700
Data Index: 4031804 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6968. Min Act: -0.1700
Data Index: 6742502 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6655. Min Act: -0.1700
Data Index: 8513773 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6343. Min Act: -0.1700
Data Index: 1468474 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0718. Min Range: -5.0718
Max Act: 4.6030. Min Act: -0.1700
Data Index: 1357787 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19