Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2688. Min Range: -5.2688
Max Act: 5.2688. Min Act: -0.1700
Data Index: 3986002 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2688. Min Range: -5.2688
Max Act: 5.1750. Min Act: -0.1700
Data Index: 4179746 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2688. Min Range: -5.2688
Max Act: 5.1125. Min Act: -0.1700
Data Index: 2357341 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2688. Min Range: -5.2688
Max Act: 5.0188. Min Act: -0.1700
Data Index: 163641 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8938. Min Act: -0.1700
Data Index: 1756841 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2333352 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2418246 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8313. Min Act: -0.1700
Data Index: 559197 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2209618 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8000. Min Act: -0.1700
Data Index: 5584630 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8000. Min Act: -0.1700
Data Index: 4222928 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2552587 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8000. Min Act: -0.1700
Data Index: 4263253 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.8000. Min Act: -0.1700
Data Index: 6674502 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7688. Min Act: -0.1700
Data Index: 6400937 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7688. Min Act: -0.1700
Data Index: 2309187 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7063. Min Act: -0.1700
Data Index: 5188915 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7063. Min Act: -0.1700
Data Index: 1037625 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7375. Min Act: -0.1700
Data Index: 8318339 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2688. Min Range: -5.2688
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1805655 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19