Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1962. Min Range: -7.1962
Max Act: 7.1962. Min Act: -0.1700
Data Index: 8426772 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1962. Min Range: -7.1962
Max Act: 7.1962. Min Act: -0.1700
Data Index: 1441012 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.8837. Min Act: -0.1700
Data Index: 3033664 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.8212. Min Act: -0.1700
Data Index: 5186237 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.7587. Min Act: -0.1700
Data Index: 568624 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.7899. Min Act: -0.1700
Data Index: 6054392 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.8524. Min Act: -0.1700
Data Index: 7622826 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6962. Min Act: -0.1700
Data Index: 3001790 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.7587. Min Act: -0.1700
Data Index: 2156769 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.7274. Min Act: -0.1700
Data Index: 382031 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6962. Min Act: -0.1700
Data Index: 1864949 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.7274. Min Act: -0.1700
Data Index: 1123266 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6024. Min Act: -0.1700
Data Index: 6967669 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6024. Min Act: -0.1700
Data Index: 3456497 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6337. Min Act: -0.1700
Data Index: 3542702 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6649. Min Act: -0.1700
Data Index: 929913 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.5399. Min Act: -0.1700
Data Index: 1531173 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6649. Min Act: -0.1700
Data Index: 6041561 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.6024. Min Act: -0.1700
Data Index: 6337330 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1962. Min Range: -7.1962
Max Act: 6.5399. Min Act: -0.1700
Data Index: 3270106 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19