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

Dataset: The Pile

Neuron 2051 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: 3.2328. Min Range: -3.2328

Max Act: 3.2328. Min Act: -0.0000

Data Index: 1910176 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 3.2328. Min Range: -3.2328

Max Act: 3.1445. Min Act: -0.0000

Data Index: 419215 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 3.2328. Min Range: -3.2328

Max Act: 3.2182. Min Act: -0.0000

Data Index: 884707 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.9135. Min Act: -0.0000

Data Index: 647931 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 3.2328. Min Range: -3.2328

Max Act: 3.1513. Min Act: -0.0000

Data Index: 114446 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.8623. Min Act: -0.0000

Data Index: 1166756 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.7709. Min Act: -0.0000

Data Index: 641163 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.7265. Min Act: -0.0000

Data Index: 1888302 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.8103. Min Act: -0.0000

Data Index: 967025 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.8606. Min Act: -0.0000

Data Index: 1924821 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.6567. Min Act: -0.0000

Data Index: 201812 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.8028. Min Act: -0.0000

Data Index: 1980043 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.5265. Min Act: -0.0000

Data Index: 1093454 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.5025. Min Act: -0.0000

Data Index: 626036 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.4935. Min Act: -0.0000

Data Index: 603258 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.7173. Min Act: -0.0000

Data Index: 989765 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.4193. Min Act: -0.0000

Data Index: 1962857 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.5625. Min Act: -0.0000

Data Index: 528884 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.5136. Min Act: -0.0000

Data Index: 951490 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 3.2328. Min Range: -3.2328

Max Act: 2.6425. Min Act: -0.0000

Data Index: 308455 (The Pile)

Max Activating Token Index: 435