Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1914782 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1181529 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.2439. Min Act: -0.0000

Data Index: 223215 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1934477 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.0501. Min Act: -0.0000

Data Index: 22514 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1311208 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.9118. Min Act: -0.0000

Data Index: 475308 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.6509. Min Range: -1.6509

Max Act: 1.0101. Min Act: -0.0001

Data Index: 1837419 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.9454. Min Act: -0.0000

Data Index: 894306 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.9909. Min Act: -0.0000

Data Index: 529688 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.7742. Min Act: -0.0000

Data Index: 122556 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1639003 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1627480 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1479419 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1431766 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1045715 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.5317. Min Act: -0.0000

Data Index: 226424 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.6068. Min Act: -0.0000

Data Index: 566646 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1476608 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.6509. Min Range: -1.6509

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1331989 (The Pile)

Max Activating Token Index: 576