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

Dataset: The Pile

Neuron 518 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: 0.6234. Min Range: -0.6234

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1671732 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5671. Min Act: -0.0000

Data Index: 261825 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5809. Min Act: -0.0000

Data Index: 848784 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5870. Min Act: -0.0000

Data Index: 382778 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1647370 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1789762 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5541. Min Act: -0.0000

Data Index: 946052 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1025532 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1492585 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5146. Min Act: -0.0000

Data Index: 376971 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1350114 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1904167 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.5313. Min Act: -0.0000

Data Index: 705315 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1457285 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1641457 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4994. Min Act: -0.0000

Data Index: 283500 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1462735 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4976. Min Act: -0.0000

Data Index: 806225 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1995282 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.6234. Min Range: -0.6234

Max Act: 0.4679. Min Act: -0.0000

Data Index: 286899 (The Pile)

Max Activating Token Index: 280