Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0563. Min Range: -1.0563

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1748412 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1643232 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1876124 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.6528. Min Act: -0.0000

Data Index: 883925 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1040938 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.6357. Min Act: -0.0000

Data Index: 325028 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5627. Min Act: -0.0000

Data Index: 542337 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5201. Min Act: -0.0000

Data Index: 337662 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5286. Min Act: -0.0000

Data Index: 893400 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1514237 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5177. Min Act: -0.0000

Data Index: 577973 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1559039 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1433482 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1181005 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1496579 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1350077 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1086809 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1757563 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1102352 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 1.0563. Min Range: -1.0563

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1479027 (The Pile)

Max Activating Token Index: 929