Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2779. Min Act: -0.1700
Data Index: 1011893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2779. Min Act: -0.1700
Data Index: 3786267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2779. Min Act: -0.1700
Data Index: 3581569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2465. Min Act: -0.1700
Data Index: 8717885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2465. Min Act: -0.1700
Data Index: 5654317 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2465. Min Act: -0.1700
Data Index: 625616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2465. Min Act: -0.1700
Data Index: 2607035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 7279557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 7864208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 6472564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 5991369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 2816330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 2283669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 4958904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.2151. Min Act: -0.1700
Data Index: 8688735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1836. Min Act: -0.1700
Data Index: 719919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1836. Min Act: -0.1700
Data Index: 4266887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1836. Min Act: -0.1700
Data Index: 6339630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1836. Min Act: -0.1700
Data Index: 1477684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2779. Min Range: -3.2779
Max Act: 3.1522. Min Act: -0.1700
Data Index: 3815636 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19