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

Dataset: The Pile

Neuron 3432 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: 0.2213. Min Range: -0.2213

Max Act: 0.2213. Min Act: -0.0000

Data Index: 572550 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1464526 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1998507 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1708. Min Act: -0.0000

Data Index: 941177 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1685. Min Act: -0.0000

Data Index: 303393 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1396965 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1179. Min Act: -0.0000

Data Index: 765189 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1192715 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1047. Min Act: -0.0000

Data Index: 338079 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0965. Min Act: -0.0000

Data Index: 886231 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0845. Min Act: -0.0000

Data Index: 636452 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0910. Min Act: -0.0000

Data Index: 22640 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1087324 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0889. Min Act: -0.0000

Data Index: 792563 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0915. Min Act: -0.0000

Data Index: 340914 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1244685 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1018697 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1004263 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0934. Min Act: -0.0000

Data Index: 350566 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.0864. Min Act: -0.0000

Data Index: 315510 (The Pile)

Max Activating Token Index: 536