Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.6918. Min Act: -0.1700
Data Index: 3166941 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.5043. Min Act: -0.1700
Data Index: 6562501 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.4106. Min Act: -0.1700
Data Index: 3491333 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.4106. Min Act: -0.1700
Data Index: 2602734 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.4106. Min Act: -0.1700
Data Index: 8100450 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.3481. Min Act: -0.1700
Data Index: 3829855 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.3168. Min Act: -0.1700
Data Index: 2436256 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2856. Min Act: -0.1700
Data Index: 1824396 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2856. Min Act: -0.1700
Data Index: 1766541 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 1084716 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 2433636 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 4114869 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 7418403 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 3504008 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.1293. Min Act: -0.1700
Data Index: 8488884 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.1606. Min Act: -0.1700
Data Index: 2575686 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.1606. Min Act: -0.1700
Data Index: 7620800 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.1293. Min Act: -0.1700
Data Index: 8076635 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.0981. Min Act: -0.1700
Data Index: 4992054 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6918. Min Range: -7.6918
Max Act: 7.0981. Min Act: -0.1700
Data Index: 5842209 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19