Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2755. Min Range: -4.2755
Max Act: 4.2755. Min Act: -0.1700
Data Index: 8052039 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2755. Min Range: -4.2755
Max Act: 4.1036. Min Act: -0.1700
Data Index: 2596651 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2755. Min Range: -4.2755
Max Act: 4.1036. Min Act: -0.1700
Data Index: 6793780 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2755. Min Range: -4.2755
Max Act: 4.1036. Min Act: -0.1700
Data Index: 5989085 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.9004. Min Act: -0.1700
Data Index: 7970131 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.8848. Min Act: -0.1700
Data Index: 1858095 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.8535. Min Act: -0.1700
Data Index: 4843684 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4387611 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.8066. Min Act: -0.1700
Data Index: 3119786 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7910. Min Act: -0.1700
Data Index: 54349 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7910. Min Act: -0.1700
Data Index: 1139634 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4429483 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.8066. Min Act: -0.1700
Data Index: 2975737 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.8066. Min Act: -0.1700
Data Index: 5529417 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7597. Min Act: -0.1700
Data Index: 565571 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7597. Min Act: -0.1700
Data Index: 2737952 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7441. Min Act: -0.1700
Data Index: 6658859 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7753. Min Act: -0.1700
Data Index: 5483041 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7753. Min Act: -0.1700
Data Index: 7437185 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2755. Min Range: -4.2755
Max Act: 3.7753. Min Act: -0.1700
Data Index: 6309815 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19