Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0285. Min Range: -5.0285
Max Act: 5.0285. Min Act: -0.1700
Data Index: 3958757 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.6847. Min Act: -0.1700
Data Index: 1372902 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.6534. Min Act: -0.1700
Data Index: 2926565 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5909. Min Act: -0.1700
Data Index: 2861155 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5597. Min Act: -0.1700
Data Index: 4638955 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5909. Min Act: -0.1700
Data Index: 2398042 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5909. Min Act: -0.1700
Data Index: 884157 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5284. Min Act: -0.1700
Data Index: 5094073 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5597. Min Act: -0.1700
Data Index: 4845662 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.5597. Min Act: -0.1700
Data Index: 472187 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4972. Min Act: -0.1700
Data Index: 934752 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4347. Min Act: -0.1700
Data Index: 1226055 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 4101032 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 772712 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 6378758 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4347. Min Act: -0.1700
Data Index: 4690407 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 8717664 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 6123780 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4659. Min Act: -0.1700
Data Index: 6243992 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0285. Min Range: -5.0285
Max Act: 4.4034. Min Act: -0.1700
Data Index: 2324441 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19