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

Dataset: The Pile

Neuron 485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.8429. Min Act: -0.0000

Data Index: 152762 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6415. Min Act: -0.0000

Data Index: 385638 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1450793 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1062027 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5889. Min Act: -0.0000

Data Index: 647423 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1734229 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1247362 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1057571 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5238. Min Act: -0.0000

Data Index: 417034 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1820526 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5199. Min Act: -0.0000

Data Index: 406594 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4853. Min Act: -0.0000

Data Index: 32737 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4917. Min Act: 0.0000

Data Index: 1677379 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.5196. Min Act: -0.0000

Data Index: 622458 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4385. Min Act: -0.0000

Data Index: 246606 (The Pile)

Max Activating Token Index: 623

Text #15

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4852. Min Act: -0.0000

Data Index: 420301 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1639764 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4501. Min Act: -0.0000

Data Index: 470440 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1006683 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.8429. Min Range: -0.8429

Max Act: 0.4256. Min Act: -0.0000

Data Index: 304897 (The Pile)

Max Activating Token Index: 772