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

Dataset: The Pile

Neuron 2915 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: 1.1760. Min Range: -1.1760

Max Act: 1.1246. Min Act: -0.0000

Data Index: 554140 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1726305 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.1127. Min Act: -0.0000

Data Index: 266368 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.1760. Min Act: -0.0000

Data Index: 260233 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0965. Min Act: -0.0000

Data Index: 1678007 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0985. Min Act: -0.0000

Data Index: 227674 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0898. Min Act: -0.0000

Data Index: 599503 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0289. Min Act: 0.0000

Data Index: 1909526 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.1564. Min Act: -0.0000

Data Index: 325918 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0521. Min Act: -0.0000

Data Index: 622733 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0414. Min Act: -0.0000

Data Index: 720523 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0264. Min Act: -0.0000

Data Index: 874367 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9702. Min Act: -0.0000

Data Index: 561136 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1006331 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1050863 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1756196 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1361266 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9149. Min Act: -0.0000

Data Index: 951277 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9727. Min Act: -0.0000

Data Index: 291093 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9041. Min Act: -0.0000

Data Index: 358764 (The Pile)

Max Activating Token Index: 557