Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4228 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.2779. Min Act: -0.1700
Data Index: 6891417 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.1217. Min Act: -0.1700
Data Index: 1703930 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.0904. Min Act: -0.1700
Data Index: 143213 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.0904. Min Act: -0.1700
Data Index: 1617199 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.0592. Min Act: -0.1700
Data Index: 6403617 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2779. Min Range: -6.2779
Max Act: 6.0279. Min Act: -0.1700
Data Index: 106174 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9967. Min Act: -0.1700
Data Index: 383249 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9967. Min Act: -0.1700
Data Index: 8230438 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9967. Min Act: -0.1700
Data Index: 7792123 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9654. Min Act: -0.1700
Data Index: 3067212 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9654. Min Act: -0.1700
Data Index: 7749403 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9654. Min Act: -0.1700
Data Index: 520295 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9342. Min Act: -0.1700
Data Index: 6388304 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9029. Min Act: -0.1700
Data Index: 3454644 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9342. Min Act: -0.1700
Data Index: 8317010 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.8717. Min Act: -0.1700
Data Index: 2370164 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.9029. Min Act: -0.1700
Data Index: 343649 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.8717. Min Act: -0.1700
Data Index: 3442768 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.8717. Min Act: -0.1700
Data Index: 8467753 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2779. Min Range: -6.2779
Max Act: 5.8717. Min Act: -0.1700
Data Index: 1853684 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19