Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.9127. Min Act: -0.1700
Data Index: 1774025 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6938. Min Act: -0.1700
Data Index: 5755478 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6625. Min Act: -0.1700
Data Index: 5755481 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6625. Min Act: -0.1700
Data Index: 5755484 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6625. Min Act: -0.1700
Data Index: 7756890 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6468. Min Act: -0.1700
Data Index: 1774032 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6312. Min Act: -0.1700
Data Index: 5755480 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.6155. Min Act: -0.1700
Data Index: 7330274 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5999. Min Act: -0.1700
Data Index: 4918171 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5999. Min Act: -0.1700
Data Index: 2789866 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5686. Min Act: -0.1700
Data Index: 1990779 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5842. Min Act: -0.1700
Data Index: 2183009 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5686. Min Act: -0.1700
Data Index: 3796986 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5216. Min Act: -0.1700
Data Index: 5080533 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5373. Min Act: -0.1700
Data Index: 2291187 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5529. Min Act: -0.1700
Data Index: 1932766 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5216. Min Act: -0.1700
Data Index: 4342628 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5216. Min Act: -0.1700
Data Index: 6886742 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5059. Min Act: -0.1700
Data Index: 5820410 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9127. Min Range: -3.9127
Max Act: 3.5216. Min Act: -0.1700
Data Index: 5858850 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19