Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0666. Min Range: -6.0666
Max Act: 6.0666. Min Act: -0.1700
Data Index: 1375117 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.8791. Min Act: -0.1700
Data Index: 5805032 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.8478. Min Act: -0.1700
Data Index: 153559 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.7853. Min Act: -0.1700
Data Index: 4464151 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.7228. Min Act: -0.1700
Data Index: 7567231 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6603. Min Act: -0.1700
Data Index: 7811607 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6603. Min Act: -0.1700
Data Index: 2054898 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6291. Min Act: -0.1700
Data Index: 5043769 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6603. Min Act: -0.1700
Data Index: 6207775 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6291. Min Act: -0.1700
Data Index: 2450254 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6291. Min Act: -0.1700
Data Index: 7417732 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.6291. Min Act: -0.1700
Data Index: 3626166 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5978. Min Act: -0.1700
Data Index: 3699339 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5666. Min Act: -0.1700
Data Index: 8063725 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5666. Min Act: -0.1700
Data Index: 4381929 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5353. Min Act: -0.1700
Data Index: 6791152 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5353. Min Act: -0.1700
Data Index: 2762576 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5041. Min Act: -0.1700
Data Index: 8409277 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.5041. Min Act: -0.1700
Data Index: 8806692 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0666. Min Range: -6.0666
Max Act: 5.4728. Min Act: -0.1700
Data Index: 4257578 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19