Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0334. Min Range: -6.0334
Max Act: 6.0334. Min Act: -0.1700
Data Index: 572773 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8771. Min Act: -0.1700
Data Index: 2780013 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.8459. Min Act: -0.1700
Data Index: 4931121 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5446525 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7834. Min Act: -0.1700
Data Index: 1724100 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.7209. Min Act: -0.1700
Data Index: 3421723 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6896. Min Act: -0.1700
Data Index: 7671097 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6896. Min Act: -0.1700
Data Index: 6796391 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6896. Min Act: -0.1700
Data Index: 6596406 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6271. Min Act: -0.1700
Data Index: 962532 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6271. Min Act: -0.1700
Data Index: 1162627 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6271. Min Act: -0.1700
Data Index: 2850114 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.6271. Min Act: -0.1700
Data Index: 6806068 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5646. Min Act: -0.1700
Data Index: 7096899 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5646. Min Act: -0.1700
Data Index: 2814426 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5334. Min Act: -0.1700
Data Index: 7139491 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5021. Min Act: -0.1700
Data Index: 7667609 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5334. Min Act: -0.1700
Data Index: 5007552 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5334. Min Act: -0.1700
Data Index: 4540905 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0334. Min Range: -6.0334
Max Act: 5.5021. Min Act: -0.1700
Data Index: 3059282 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19