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

Dataset: The Pile

Neuron 1300 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: 1.2267. Min Range: -1.2267

Max Act: 1.2267. Min Act: -0.0000

Data Index: 128400 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0799. Min Act: -0.0000

Data Index: 53751 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0819. Min Act: -0.0000

Data Index: 671677 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1760975 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1713820 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8278. Min Act: -0.0000

Data Index: 377770 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1159860 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8266. Min Act: -0.0000

Data Index: 843787 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 1.2267. Min Range: -1.2267

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1254493 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8598. Min Act: -0.0000

Data Index: 761553 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8720. Min Act: -0.0000

Data Index: 949797 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.7690. Min Act: -0.0000

Data Index: 393181 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1461948 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8303. Min Act: -0.0000

Data Index: 686950 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1582875 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1430255 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8345. Min Act: -0.0000

Data Index: 19703 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1688321 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1994209 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 1.2267. Min Range: -1.2267

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1042795 (The Pile)

Max Activating Token Index: 763