Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 599 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.2014. Min Act: -0.1700
Data Index: 2721884 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1857. Min Act: -0.1700
Data Index: 1703640 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1699. Min Act: -0.1700
Data Index: 8429229 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1385. Min Act: -0.1700
Data Index: 70604 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1542. Min Act: -0.1700
Data Index: 4100651 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1385. Min Act: -0.1699
Data Index: 1271109 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1385. Min Act: -0.1700
Data Index: 4037034 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1542. Min Act: -0.1700
Data Index: 6412588 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1227. Min Act: -0.1700
Data Index: 1827286 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1070. Min Act: -0.1700
Data Index: 5316611 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0912. Min Act: -0.1691
Data Index: 8749542 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1070. Min Act: -0.1700
Data Index: 2106591 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0912. Min Act: -0.1700
Data Index: 6207451 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.1070. Min Act: -0.1700
Data Index: 3805496 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0439. Min Act: -0.1700
Data Index: 627935 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0439. Min Act: -0.1700
Data Index: 5971431 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0123. Min Act: -0.1700
Data Index: 3140862 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0281. Min Act: -0.1700
Data Index: 3725182 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0281. Min Act: -0.1700
Data Index: 7186737 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2014. Min Range: -3.2014
Max Act: 3.0123. Min Act: -0.1700
Data Index: 4210190 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19