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

Dataset: The Pile

Neuron 5104 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2716. Min Range: -1.2716

Max Act: 1.2716. Min Act: -0.0000

Data Index: 666011 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 1.2716. Min Range: -1.2716

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1621288 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.2716. Min Range: -1.2716

Max Act: 1.1684. Min Act: -0.0000

Data Index: 648915 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9323. Min Act: -0.0000

Data Index: 513590 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1357799 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1108056 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8721. Min Act: -0.0000

Data Index: 13621 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.9773. Min Act: -0.0000

Data Index: 803176 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8444. Min Act: -0.0000

Data Index: 908900 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1847217 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1233142 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1385000 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7547. Min Act: -0.0000

Data Index: 7115 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.8281. Min Act: -0.0000

Data Index: 747982 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6888. Min Act: -0.0000

Data Index: 952978 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1879218 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1086828 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1058615 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.7195. Min Act: -0.0000

Data Index: 61460 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.2716. Min Range: -1.2716

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1147994 (The Pile)

Max Activating Token Index: 352