Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1282 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.7066. Min Act: -0.1700
Data Index: 3813848 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.7066. Min Act: -0.1700
Data Index: 2328994 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.6441. Min Act: -0.1700
Data Index: 1265793 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.6441. Min Act: -0.1700
Data Index: 4200359 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.4566. Min Act: -0.1700
Data Index: 6177372 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.4566. Min Act: -0.1700
Data Index: 598222 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.4566. Min Act: -0.1700
Data Index: 8667982 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.4566. Min Act: -0.1700
Data Index: 1724362 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3941. Min Act: -0.1700
Data Index: 7233473 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 5521395 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 8278919 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 622082 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 2907368 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 6888093 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.3316. Min Act: -0.1700
Data Index: 1146177 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.2691. Min Act: -0.1700
Data Index: 5938878 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.2691. Min Act: -0.1700
Data Index: 2894814 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.2066. Min Act: -0.1700
Data Index: 3271941 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.1754. Min Act: -0.1700
Data Index: 6916558 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7066. Min Range: -7.7066
Max Act: 7.2066. Min Act: -0.1700
Data Index: 734358 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19