Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0308. Min Range: -6.0308
Max Act: 6.0308. Min Act: -0.1700
Data Index: 8067468 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.9371. Min Act: -0.1700
Data Index: 5555141 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.9058. Min Act: -0.1700
Data Index: 5843861 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1641307 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.9058. Min Act: -0.1700
Data Index: 8013477 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1268727 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1001972 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8433. Min Act: -0.1700
Data Index: 345405 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8746. Min Act: -0.1700
Data Index: 1001973 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5747595 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7808. Min Act: -0.1700
Data Index: 3053176 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7496. Min Act: -0.1700
Data Index: 8425060 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7183. Min Act: -0.1700
Data Index: 7657916 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7183. Min Act: -0.1700
Data Index: 5843844 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.7183. Min Act: -0.1700
Data Index: 1268862 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6292223 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6558. Min Act: -0.1700
Data Index: 2878002 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5747600 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 3927460 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0308. Min Range: -6.0308
Max Act: 5.6871. Min Act: -0.1700
Data Index: 894805 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19