Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4063. Min Range: -8.4063
Max Act: 8.4063. Min Act: -0.1698
Data Index: 7394295 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4063. Min Range: -8.4063
Max Act: 8.2188. Min Act: -0.1700
Data Index: 7611372 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.9063. Min Act: -0.1700
Data Index: 6278995 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.6563. Min Act: -0.1700
Data Index: 8472415 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.6563. Min Act: -0.1700
Data Index: 448814 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.5938. Min Act: -0.1700
Data Index: 4058577 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.6563. Min Act: -0.1700
Data Index: 1950936 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.5313. Min Act: -0.1700
Data Index: 411935 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.5938. Min Act: -0.1700
Data Index: 1409049 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.5313. Min Act: -0.1700
Data Index: 1691257 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.5001. Min Act: -0.1700
Data Index: 1289395 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.4376. Min Act: -0.1700
Data Index: 6250659 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3751. Min Act: -0.1700
Data Index: 8724118 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3751. Min Act: -0.1700
Data Index: 8671288 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3438. Min Act: -0.1700
Data Index: 7189875 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3438. Min Act: -0.1700
Data Index: 8106191 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3438. Min Act: -0.1700
Data Index: 6647999 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.2813. Min Act: -0.1700
Data Index: 3955712 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.3126. Min Act: -0.1700
Data Index: 880397 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4063. Min Range: -8.4063
Max Act: 7.2813. Min Act: -0.1700
Data Index: 7714370 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19