Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.8512. Min Act: -0.1700
Data Index: 5779295 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7717. Min Act: -0.1697
Data Index: 3576663 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7557. Min Act: -0.1700
Data Index: 35839 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7717. Min Act: -0.1700
Data Index: 3962201 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7398. Min Act: -0.1700
Data Index: 3294213 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7078. Min Act: -0.1700
Data Index: 4396443 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7398. Min Act: -0.1697
Data Index: 5638833 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7078. Min Act: -0.1700
Data Index: 4664241 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7238. Min Act: -0.1700
Data Index: 1746688 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7238. Min Act: -0.1696
Data Index: 2347847 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6918. Min Act: -0.1700
Data Index: 1645798 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6597. Min Act: -0.1700
Data Index: 6059437 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1700
Data Index: 3510510 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1700
Data Index: 7058841 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1697
Data Index: 4752590 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1700
Data Index: 1113420 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.7078. Min Act: -0.1700
Data Index: 7092720 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1684
Data Index: 5841408 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6597. Min Act: -0.1700
Data Index: 6145425 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8512. Min Range: -2.8512
Max Act: 2.6758. Min Act: -0.1700
Data Index: 5906801 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19