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

Dataset: The Pile

Neuron 1105 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: 1.2035. Min Range: -1.2035

Max Act: 1.2035. Min Act: -0.0000

Data Index: 796612 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0590. Min Act: -0.0000

Data Index: 262382 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1702282 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1744637 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.1249. Min Act: -0.0000

Data Index: 610935 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1455163 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9686. Min Act: -0.0000

Data Index: 376550 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1131092 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9755. Min Act: -0.0000

Data Index: 663509 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9750. Min Act: -0.0000

Data Index: 336000 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9689. Min Act: -0.0000

Data Index: 673703 (The Pile)

Max Activating Token Index: 244

Text #11

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9759. Min Act: -0.0000

Data Index: 783510 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9727. Min Act: -0.0000

Data Index: 299563 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1148699 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1750334 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8957. Min Act: -0.0000

Data Index: 844960 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1184268 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9151. Min Act: -0.0000

Data Index: 923079 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1592916 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9345. Min Act: -0.0000

Data Index: 42199 (The Pile)

Max Activating Token Index: 81