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

Dataset: The Pile

Neuron 3195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3281. Min Range: -5.3281

Max Act: 5.3281. Min Act: -0.0000

Data Index: 1731408 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.6592. Min Act: -0.0000

Data Index: 151223 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.4843. Min Act: -0.0000

Data Index: 1567963 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.8738. Min Act: -0.0000

Data Index: 1410096 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.2757. Min Act: -0.0000

Data Index: 573165 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.6046. Min Act: -0.0000

Data Index: 427684 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.4216. Min Act: -0.0000

Data Index: 645727 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.2302. Min Act: -0.0000

Data Index: 1656748 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1891. Min Act: -0.0000

Data Index: 1833994 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1314. Min Act: -0.0000

Data Index: 251729 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1767. Min Act: -0.0000

Data Index: 1686025 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1879. Min Act: -0.0000

Data Index: 1866584 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.3227. Min Act: -0.0000

Data Index: 320744 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.3133. Min Act: -0.0000

Data Index: 103587 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9269. Min Act: -0.0000

Data Index: 1755717 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.0829. Min Act: -0.0000

Data Index: 102833 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.1883. Min Act: -0.0000

Data Index: 1995116 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 5.3281. Min Range: -5.3281

Max Act: 4.0012. Min Act: -0.0000

Data Index: 389400 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9741. Min Act: -0.0000

Data Index: 971283 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 5.3281. Min Range: -5.3281

Max Act: 3.9487. Min Act: -0.0000

Data Index: 1780163 (The Pile)

Max Activating Token Index: 601