Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.1997. Min Act: -0.1700
Data Index: 1463781 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.1997. Min Act: -0.1700
Data Index: 5634701 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.1685. Min Act: -0.1700
Data Index: 2031284 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.0747. Min Act: -0.1700
Data Index: 7247237 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.0122. Min Act: -0.1700
Data Index: 7464835 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.0122. Min Act: -0.1700
Data Index: 4315649 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1997. Min Range: -5.1997
Max Act: 5.0122. Min Act: -0.1700
Data Index: 10359 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.9810. Min Act: -0.1700
Data Index: 3401720 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.9810. Min Act: -0.1700
Data Index: 6383495 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.9810. Min Act: -0.1700
Data Index: 5888102 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.9810. Min Act: -0.1700
Data Index: 629927 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2705695 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8872. Min Act: -0.1700
Data Index: 8593696 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8872. Min Act: -0.1700
Data Index: 2231284 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8247. Min Act: -0.1700
Data Index: 358765 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8560. Min Act: -0.1700
Data Index: 4036015 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3651137 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8560. Min Act: -0.1700
Data Index: 7793584 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8560. Min Act: -0.1700
Data Index: 8808261 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1997. Min Range: -5.1997
Max Act: 4.8560. Min Act: -0.1700
Data Index: 3491759 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19