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

Dataset: The Pile

Neuron 3468 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: 0.8038. Min Range: -0.8038

Max Act: 0.7866. Min Act: -0.0000

Data Index: 969112 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1741725 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1254765 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7286. Min Act: -0.0000

Data Index: 901691 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7189. Min Act: 0.0000

Data Index: 1890432 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1503338 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1345285 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6630. Min Act: -0.0000

Data Index: 617168 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1460946 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1169580 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6459. Min Act: 0.0000

Data Index: 1794860 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1243402 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6315. Min Act: 0.0000

Data Index: 335222 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6052. Min Act: 0.0001

Data Index: 1784162 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6037. Min Act: -0.0000

Data Index: 589653 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5952. Min Act: -0.0000

Data Index: 910019 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6222. Min Act: -0.0000

Data Index: 44381 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6228. Min Act: -0.0000

Data Index: 966477 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1340647 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.5851. Min Act: 0.0000

Data Index: 347603 (The Pile)

Max Activating Token Index: 120