Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2007. Min Range: -9.2007
Max Act: 9.2007. Min Act: -0.1700
Data Index: 3124167 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.9507. Min Act: -0.1700
Data Index: 8548142 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.8882. Min Act: -0.1700
Data Index: 6073244 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.8257. Min Act: -0.1700
Data Index: 2746512 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.8257. Min Act: -0.1700
Data Index: 8811943 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.7632. Min Act: -0.1700
Data Index: 25640 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.7007. Min Act: -0.1700
Data Index: 8246524 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.7007. Min Act: -0.1700
Data Index: 5650663 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.6382. Min Act: -0.1700
Data Index: 5336508 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.6382. Min Act: -0.1700
Data Index: 2617846 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.6382. Min Act: -0.1700
Data Index: 5335332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.6382. Min Act: -0.1699
Data Index: 7769293 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.5757. Min Act: -0.1700
Data Index: 1574140 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.5757. Min Act: -0.1700
Data Index: 8350078 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.5757. Min Act: -0.1700
Data Index: 7096581 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.5132. Min Act: -0.1700
Data Index: 7556142 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.4507. Min Act: -0.1700
Data Index: 3832649 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.4507. Min Act: -0.1700
Data Index: 3384907 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.4507. Min Act: -0.1700
Data Index: 3562741 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2007. Min Range: -9.2007
Max Act: 8.3882. Min Act: -0.1700
Data Index: 3144044 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19