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

Dataset: The Pile

Neuron 4309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.7441. Min Act: -0.0000

Data Index: 86934 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1865321 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1707968 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.7063. Min Act: -0.0000

Data Index: 427723 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.8128. Min Act: -0.0000

Data Index: 428080 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5607. Min Act: -0.0000

Data Index: 1214586 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5518. Min Act: -0.0000

Data Index: 1905343 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1548367 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5727. Min Act: -0.0000

Data Index: 235896 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5596. Min Act: -0.0000

Data Index: 826821 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1960851 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5890. Min Act: -0.0000

Data Index: 258901 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.5457. Min Act: -0.0000

Data Index: 192833 (The Pile)

Max Activating Token Index: 952

Text #13

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.3807. Min Act: -0.0000

Data Index: 433670 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.4703. Min Act: -0.0000

Data Index: 637864 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1126000 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1326303 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1694634 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.3814. Min Act: -0.0000

Data Index: 195911 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 1.8128. Min Range: -1.8128

Max Act: 1.3705. Min Act: -0.0000

Data Index: 717882 (The Pile)

Max Activating Token Index: 143