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

Dataset: The Pile

Neuron 452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.9107. Min Act: -0.0000

Data Index: 126794 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1536516 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.8200. Min Act: -0.0000

Data Index: 312759 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1199342 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1432754 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1722299 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7636. Min Act: -0.0000

Data Index: 851911 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1951089 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7501. Min Act: -0.0000

Data Index: 659042 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1532072 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7474. Min Act: -0.0000

Data Index: 124784 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1644964 (The Pile)

Max Activating Token Index: 687

Text #12

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1804832 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1193120 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7665. Min Act: -0.0000

Data Index: 140496 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1143656 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1137392 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7237. Min Act: -0.0000

Data Index: 356513 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1820698 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6809. Min Act: -0.0000

Data Index: 185714 (The Pile)

Max Activating Token Index: 649