Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1207. Min Range: -4.1207
Max Act: 4.1207. Min Act: -0.1700
Data Index: 3094772 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1207. Min Range: -4.1207
Max Act: 4.1207. Min Act: -0.1700
Data Index: 1190599 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1207. Min Range: -4.1207
Max Act: 4.0582. Min Act: -0.1700
Data Index: 1412344 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1207. Min Range: -4.1207
Max Act: 4.0269. Min Act: -0.1700
Data Index: 1035586 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.9175. Min Act: -0.1700
Data Index: 3475723 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.9332. Min Act: -0.1700
Data Index: 5461851 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.9175. Min Act: -0.1700
Data Index: 6397401 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.9175. Min Act: -0.1700
Data Index: 1588477 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8863. Min Act: -0.1700
Data Index: 7944285 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8863. Min Act: -0.1700
Data Index: 8643568 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8706. Min Act: -0.1700
Data Index: 5527926 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8394. Min Act: -0.1700
Data Index: 8319986 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8706. Min Act: -0.1700
Data Index: 5487046 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8550. Min Act: -0.1700
Data Index: 8043732 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8237. Min Act: -0.1700
Data Index: 6200613 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8237. Min Act: -0.1700
Data Index: 4032446 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8081. Min Act: -0.1700
Data Index: 6126471 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.7925. Min Act: -0.1700
Data Index: 3091793 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.8081. Min Act: -0.1700
Data Index: 1589565 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1207. Min Range: -4.1207
Max Act: 3.7768. Min Act: -0.1700
Data Index: 5119206 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19