Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 391 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2016. Min Range: -6.2016
Max Act: 6.2016. Min Act: -0.1700
Data Index: 3064526 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2016. Min Range: -6.2016
Max Act: 6.1704. Min Act: -0.1700
Data Index: 2395386 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2016. Min Range: -6.2016
Max Act: 6.0766. Min Act: -0.1700
Data Index: 6178291 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.9204. Min Act: -0.1700
Data Index: 2631150 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 6148112 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 2442698 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 3733474 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 8332141 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 5204331 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8891. Min Act: -0.1700
Data Index: 7169150 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8579. Min Act: -0.1700
Data Index: 1302463 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8266. Min Act: -0.1700
Data Index: 922527 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8266. Min Act: -0.1700
Data Index: 7699386 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.8266. Min Act: -0.1700
Data Index: 5756181 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7641. Min Act: -0.1700
Data Index: 3599875 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7641. Min Act: -0.1700
Data Index: 1162215 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7954. Min Act: -0.1700
Data Index: 4556084 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4605530 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7329. Min Act: -0.1700
Data Index: 3301262 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2016. Min Range: -6.2016
Max Act: 5.7016. Min Act: -0.1700
Data Index: 8482924 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19