Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1479. Min Range: -10.1479
Max Act: 10.1479. Min Act: -0.1700
Data Index: 3607137 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.7729. Min Act: -0.1700
Data Index: 4022122 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.7104. Min Act: -0.1700
Data Index: 275638 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.7104. Min Act: -0.1700
Data Index: 6293398 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.7104. Min Act: -0.1700
Data Index: 979300 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.6479. Min Act: -0.1700
Data Index: 4576813 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.7104. Min Act: -0.1700
Data Index: 5106269 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.5854. Min Act: -0.1700
Data Index: 3486625 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.5229. Min Act: -0.1700
Data Index: 4529284 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.5229. Min Act: -0.1700
Data Index: 4975720 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.5229. Min Act: -0.1700
Data Index: 4519081 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.4604. Min Act: -0.1700
Data Index: 7212255 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.4604. Min Act: -0.1700
Data Index: 3819863 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3979. Min Act: -0.1700
Data Index: 7590706 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3979. Min Act: -0.1700
Data Index: 8703337 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3979. Min Act: -0.1700
Data Index: 2568810 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3979. Min Act: -0.1700
Data Index: 7464437 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3354. Min Act: -0.1700
Data Index: 1876024 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3354. Min Act: -0.1700
Data Index: 5941054 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1479. Min Range: -10.1479
Max Act: 9.3979. Min Act: -0.1700
Data Index: 3808779 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19