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

Dataset: The Pile

Neuron 2474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.1757. Min Act: -0.0000

Data Index: 803256 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8210. Min Act: -0.0000

Data Index: 652606 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.1574. Min Act: -0.0000

Data Index: 1419931 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.0182. Min Act: -0.0000

Data Index: 447511 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.0802. Min Act: -0.0000

Data Index: 365856 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.5348. Min Act: -0.0000

Data Index: 662170 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.5650. Min Act: -0.0000

Data Index: 1156089 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.8263. Min Act: -0.0000

Data Index: 878221 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.3243. Min Act: -0.0000

Data Index: 1831497 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.6200. Min Act: -0.0000

Data Index: 1561433 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.6016. Min Act: -0.0000

Data Index: 1404894 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.5440. Min Act: -0.0000

Data Index: 410443 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.6555. Min Act: -0.0000

Data Index: 266500 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.5479. Min Act: -0.0000

Data Index: 632137 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.5276. Min Act: -0.0000

Data Index: 613187 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.4961. Min Act: -0.0000

Data Index: 430846 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.3271. Min Act: -0.0000

Data Index: 441392 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.3379. Min Act: -0.0000

Data Index: 460324 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 5.1757. Min Range: -5.1757

Max Act: 3.3073. Min Act: -0.0000

Data Index: 521329 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 5.1757. Min Range: -5.1757

Max Act: 2.9993. Min Act: -0.0000

Data Index: 1396800 (The Pile)

Max Activating Token Index: 956