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

Dataset: The Pile

Neuron 1973 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: 1.4059. Min Range: -1.4059

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1165926 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1581934 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.3787. Min Act: -0.0000

Data Index: 235001 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1831. Min Act: -0.0000

Data Index: 680311 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1103080 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0795. Min Act: -0.0000

Data Index: 599607 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1707863 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0950. Min Act: -0.0000

Data Index: 190835 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0239. Min Act: -0.0000

Data Index: 685978 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1732876 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0171. Min Act: -0.0000

Data Index: 151756 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1028305 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0020. Min Act: -0.0000

Data Index: 744340 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1665548 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9628. Min Act: -0.0000

Data Index: 781997 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1766809 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1873811 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1753827 (The Pile)

Max Activating Token Index: 764

Text #18

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1470421 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1357487 (The Pile)

Max Activating Token Index: 475