Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.2592. Min Act: -0.1700
Data Index: 667781 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.2905. Min Act: -0.1700
Data Index: 343482 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.2280. Min Act: -0.1700
Data Index: 1627015 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1967. Min Act: -0.1700
Data Index: 250108 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7047774 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1655. Min Act: -0.1700
Data Index: 2267859 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1030. Min Act: -0.1700
Data Index: 6057788 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1655. Min Act: -0.1700
Data Index: 1627013 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3512624 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0717. Min Act: -0.1700
Data Index: 5354801 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 1627012 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0405. Min Act: -0.1700
Data Index: 631250 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0405. Min Act: -0.1700
Data Index: 4220077 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 4855614 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 2142407 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 1627014 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 667780 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 6052659 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2905. Min Range: -5.2905
Max Act: 5.0092. Min Act: -0.1700
Data Index: 670746 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2905. Min Range: -5.2905
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1622569 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19