Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 337 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1009. Min Range: -6.1009
Max Act: 6.1009. Min Act: -0.1700
Data Index: 381774 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1009. Min Range: -6.1009
Max Act: 6.0384. Min Act: -0.1700
Data Index: 8482604 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1009. Min Range: -6.1009
Max Act: 6.0072. Min Act: -0.1700
Data Index: 6784568 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9759. Min Act: -0.1700
Data Index: 6859277 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9447. Min Act: -0.1700
Data Index: 2947637 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9447. Min Act: -0.1700
Data Index: 505594 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9447. Min Act: -0.1700
Data Index: 2979781 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9134. Min Act: -0.1700
Data Index: 7995712 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.9134. Min Act: -0.1700
Data Index: 215416 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8822. Min Act: -0.1700
Data Index: 5447637 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8822. Min Act: -0.1700
Data Index: 8458770 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7373608 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 2986677 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7041205 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 4456370 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3571553 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 6124849 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8509. Min Act: -0.1700
Data Index: 2211704 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8197. Min Act: -0.1700
Data Index: 5913652 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1009. Min Range: -6.1009
Max Act: 5.8197. Min Act: -0.1700
Data Index: 6176682 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19