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

Dataset: The Pile

Neuron 3360 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1438930 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2746. Min Act: -0.0000

Data Index: 486020 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1623753 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1584736 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1676115 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1948209 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0595. Min Act: -0.0000

Data Index: 643849 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1776. Min Act: -0.0000

Data Index: 852222 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1631806 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1706812 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0879. Min Act: -0.0000

Data Index: 100598 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1415. Min Act: -0.0000

Data Index: 960328 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1557690 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0786. Min Act: -0.0000

Data Index: 884654 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1173486 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1331119 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0651. Min Act: -0.0000

Data Index: 771874 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0699. Min Act: -0.0000

Data Index: 482999 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.1008. Min Act: -0.0000

Data Index: 377157 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.5397. Min Range: -1.5397

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1666523 (The Pile)

Max Activating Token Index: 54