Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.3823. Min Act: -0.1700
Data Index: 5182427 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.2573. Min Act: -0.1700
Data Index: 4693488 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3823. Min Range: -6.3823
Max Act: 6.1323. Min Act: -0.1700
Data Index: 5536257 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.9135. Min Act: -0.1700
Data Index: 2526337 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8823. Min Act: -0.1700
Data Index: 5388969 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8510. Min Act: -0.1700
Data Index: 8675841 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.7885. Min Act: -0.1700
Data Index: 2753469 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.8198. Min Act: -0.1700
Data Index: 237862 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.7573. Min Act: -0.1700
Data Index: 412207 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6635. Min Act: -0.1700
Data Index: 2906754 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6010. Min Act: -0.1700
Data Index: 2466781 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6323. Min Act: -0.1700
Data Index: 2752443 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6010. Min Act: -0.1700
Data Index: 3860399 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6010. Min Act: -0.1700
Data Index: 1851140 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.6010. Min Act: -0.1700
Data Index: 1685341 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.5698. Min Act: -0.1700
Data Index: 8119632 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.5385. Min Act: -0.1700
Data Index: 1554698 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.5385. Min Act: -0.1700
Data Index: 1543701 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.5385. Min Act: -0.1700
Data Index: 3965194 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3823. Min Range: -6.3823
Max Act: 5.5073. Min Act: -0.1700
Data Index: 3191931 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19