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

Dataset: The Pile

Neuron 1381 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: 5.1881. Min Range: -5.1881

Max Act: 5.1881. Min Act: -0.0000

Data Index: 457073 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 5.1881. Min Range: -5.1881

Max Act: 4.0040. Min Act: -0.0000

Data Index: 827813 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.6115. Min Act: -0.0000

Data Index: 107751 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.9068. Min Act: -0.0000

Data Index: 1139718 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.6353. Min Act: -0.0000

Data Index: 553855 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.5132. Min Act: -0.0000

Data Index: 1500972 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.9553. Min Act: -0.0000

Data Index: 972333 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.8204. Min Act: -0.0000

Data Index: 884914 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.1903. Min Act: -0.0000

Data Index: 27408 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.7935. Min Act: -0.0000

Data Index: 1089710 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.8913. Min Act: -0.0000

Data Index: 1158718 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.4386. Min Act: -0.0000

Data Index: 15103 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.4282. Min Act: -0.0000

Data Index: 1500525 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1882627 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.5647. Min Act: -0.0000

Data Index: 1033239 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.7046. Min Act: -0.0000

Data Index: 435604 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.8027. Min Act: -0.0000

Data Index: 1964430 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.3562. Min Act: -0.0000

Data Index: 1822678 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 5.1881. Min Range: -5.1881

Max Act: 2.7376. Min Act: -0.0000

Data Index: 1415530 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 5.1881. Min Range: -5.1881

Max Act: 3.0397. Min Act: -0.0000

Data Index: 1050967 (The Pile)

Max Activating Token Index: 101