Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1993. Min Act: -0.1700
Data Index: 376878 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1993. Min Act: -0.1700
Data Index: 1604995 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1835. Min Act: -0.1700
Data Index: 3513871 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1678. Min Act: -0.1700
Data Index: 6902452 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1521. Min Act: -0.1700
Data Index: 6876558 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1206. Min Act: -0.1699
Data Index: 3986385 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1363. Min Act: -0.1700
Data Index: 4893456 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1206. Min Act: -0.1700
Data Index: 8049356 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.1048. Min Act: -0.1700
Data Index: 3651290 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0891. Min Act: -0.1700
Data Index: 7178175 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 8267660 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 5984866 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 2458911 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 4768946 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 351678 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0733. Min Act: -0.1700
Data Index: 8715461 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0575. Min Act: -0.1700
Data Index: 5243571 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0417. Min Act: -0.1696
Data Index: 2903813 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0417. Min Act: -0.1700
Data Index: 2157723 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1993. Min Range: -3.1993
Max Act: 3.0417. Min Act: -0.1700
Data Index: 8253454 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19