Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2276 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.5779. Min Act: -0.1700
Data Index: 8282304 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.5078. Min Act: -0.1700
Data Index: 5509964 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.5078. Min Act: -0.1700
Data Index: 2411062 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4991. Min Act: -0.1700
Data Index: 7816745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.5078. Min Act: -0.1700
Data Index: 3490087 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4903. Min Act: -0.1700
Data Index: 1774359 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4815. Min Act: -0.1700
Data Index: 2021289 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4815. Min Act: -0.1700
Data Index: 7495596 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4815. Min Act: -0.1700
Data Index: 859275 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4639. Min Act: -0.1700
Data Index: 2369789 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4727. Min Act: -0.1700
Data Index: 3629623 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4727. Min Act: -0.1700
Data Index: 1996889 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4639. Min Act: -0.1700
Data Index: 3378817 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1696
Data Index: 4382793 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1700
Data Index: 6153965 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1697
Data Index: 5825633 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1691
Data Index: 8006527 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1700
Data Index: 939696 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4463. Min Act: -0.1697
Data Index: 6793932 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5779. Min Range: -1.5779
Max Act: 1.4375. Min Act: -0.1700
Data Index: 7529712 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19