Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9566. Min Range: -8.9566
Max Act: 8.9566. Min Act: -0.1700
Data Index: 1706854 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9566. Min Range: -8.9566
Max Act: 8.2066. Min Act: -0.1700
Data Index: 1153346 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9566. Min Range: -8.9566
Max Act: 8.1441. Min Act: -0.1700
Data Index: 8073043 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.9878. Min Act: -0.1700
Data Index: 1983208 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.9253. Min Act: -0.1700
Data Index: 3308535 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.7691. Min Act: -0.1700
Data Index: 7020983 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.7691. Min Act: -0.1700
Data Index: 5620496 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.7378. Min Act: -0.1700
Data Index: 1885519 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.7066. Min Act: -0.1700
Data Index: 998307 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.7378. Min Act: -0.1700
Data Index: 664124 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.6753. Min Act: -0.1700
Data Index: 8666594 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.6128. Min Act: -0.1700
Data Index: 1638713 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.5816. Min Act: -0.1700
Data Index: 3801636 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.5816. Min Act: -0.1700
Data Index: 2469818 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.5503. Min Act: -0.1700
Data Index: 7968429 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.5191. Min Act: -0.1700
Data Index: 8310671 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.4878. Min Act: -0.1700
Data Index: 7602126 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.4566. Min Act: -0.1700
Data Index: 7235321 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.3941. Min Act: -0.1700
Data Index: 4172512 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9566. Min Range: -8.9566
Max Act: 7.3941. Min Act: -0.1700
Data Index: 1111411 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19