Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3934 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1630645 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.8214. Min Act: -0.0000

Data Index: 297648 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1355081 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1310019 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.7008. Min Act: -0.0000

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6086. Min Act: -0.0000

Data Index: 634269 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6286. Min Act: -0.0000

Data Index: 885509 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1452864 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6342. Min Act: -0.0000

Data Index: 938326 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6468. Min Act: -0.0000

Data Index: 477487 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6891. Min Act: -0.0000

Data Index: 595634 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6796. Min Act: -0.0000

Data Index: 224576 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1515808 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6793. Min Act: -0.0000

Data Index: 334414 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.5852. Min Act: -0.0000

Data Index: 401228 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6486. Min Act: -0.0000

Data Index: 996280 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.5965. Min Act: -0.0000

Data Index: 757841 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1307471 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1551414 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.8419. Min Range: -1.8419

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1387667 (Python Code)

Max Activating Token Index: 254