Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.5790. Min Act: -0.1700
Data Index: 4918029 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.5165. Min Act: -0.1700
Data Index: 3967520 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.4852. Min Act: -0.1700
Data Index: 4616446 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.3602. Min Act: -0.1700
Data Index: 2008403 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.2977. Min Act: -0.1700
Data Index: 6739877 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.2665. Min Act: -0.1700
Data Index: 1437562 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.2039. Min Act: -0.1700
Data Index: 2373866 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.2039. Min Act: -0.1700
Data Index: 5838250 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.1727. Min Act: -0.1700
Data Index: 7431327 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.1414. Min Act: -0.1700
Data Index: 5308383 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.1414. Min Act: -0.1700
Data Index: 2184650 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0789. Min Act: -0.1700
Data Index: 4898591 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0164. Min Act: -0.1700
Data Index: 4780056 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0789. Min Act: -0.1700
Data Index: 7478241 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0164. Min Act: -0.1700
Data Index: 8814037 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 4495826 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 7713344 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0789. Min Act: -0.1700
Data Index: 3462791 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 4387776 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5790. Min Range: -4.5790
Max Act: 4.0477. Min Act: -0.1700
Data Index: 7702336 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19