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

Dataset: The Pile

Neuron 4520 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1988614 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1097256 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1536624 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1700268 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2746. Min Act: 0.0000

Data Index: 151142 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1622686 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1471110 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1211472 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1615166 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1434303 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1661918 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0178. Min Act: -0.0000

Data Index: 674694 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0383. Min Act: -0.0000

Data Index: 111122 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1716774 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1964550 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 1.4625. Min Range: -1.4625

Max Act: 0.9925. Min Act: -0.0000

Data Index: 527235 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1585980 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0022. Min Act: -0.0000

Data Index: 978343 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.4625. Min Range: -1.4625

Max Act: 0.9687. Min Act: 0.0000

Data Index: 1119377 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 1.4625. Min Range: -1.4625

Max Act: 1.0211. Min Act: -0.0000

Data Index: 182093 (The Pile)

Max Activating Token Index: 270