Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.5653. Min Act: -0.1700
Data Index: 5260679 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.1903. Min Act: -0.1700
Data Index: 7586962 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.1903. Min Act: -0.1700
Data Index: 984544 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.1903. Min Act: -0.1700
Data Index: 5260678 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.1903. Min Act: -0.1700
Data Index: 7700914 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.1591. Min Act: -0.1700
Data Index: 2937834 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0966. Min Act: -0.1700
Data Index: 1761507 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 6488810 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 5277177 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 2770241 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 558470 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 1082960 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0341. Min Act: -0.1700
Data Index: 2324600 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0028. Min Act: -0.1700
Data Index: 5260682 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5653. Min Range: -6.5653
Max Act: 6.0028. Min Act: -0.1700
Data Index: 7785485 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5653. Min Range: -6.5653
Max Act: 5.9403. Min Act: -0.1700
Data Index: 3290379 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5653. Min Range: -6.5653
Max Act: 5.9716. Min Act: -0.1700
Data Index: 6403067 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5653. Min Range: -6.5653
Max Act: 5.9716. Min Act: -0.1700
Data Index: 8113722 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5653. Min Range: -6.5653
Max Act: 5.9403. Min Act: -0.1700
Data Index: 1437776 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5653. Min Range: -6.5653
Max Act: 5.9403. Min Act: -0.1700
Data Index: 7142141 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19