Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3041. Min Range: -5.3041
Max Act: 5.3041. Min Act: -0.1700
Data Index: 7084977 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3041. Min Range: -5.3041
Max Act: 5.2103. Min Act: -0.1700
Data Index: 4834865 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3041. Min Range: -5.3041
Max Act: 5.0853. Min Act: -0.1700
Data Index: 1807219 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3041. Min Range: -5.3041
Max Act: 5.0541. Min Act: -0.1700
Data Index: 3467874 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.9916. Min Act: -0.1700
Data Index: 2228865 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.9291. Min Act: -0.1700
Data Index: 1695686 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.9291. Min Act: -0.1700
Data Index: 1528761 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8666. Min Act: -0.1700
Data Index: 5417733 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8978. Min Act: -0.1700
Data Index: 2963006 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8978. Min Act: -0.1700
Data Index: 8695683 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8666. Min Act: -0.1700
Data Index: 4138336 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8666. Min Act: -0.1700
Data Index: 7833332 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8353. Min Act: -0.1700
Data Index: 1711691 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8353. Min Act: -0.1700
Data Index: 6247516 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8353. Min Act: -0.1700
Data Index: 1307959 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8353. Min Act: -0.1700
Data Index: 1770860 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.7728. Min Act: -0.1700
Data Index: 4425585 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8041. Min Act: -0.1700
Data Index: 2157863 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8041. Min Act: -0.1700
Data Index: 4687810 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3041. Min Range: -5.3041
Max Act: 4.8041. Min Act: -0.1700
Data Index: 6699233 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19