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

Dataset: The Pile

Neuron 4225 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: 3.5963. Min Range: -3.5963

Max Act: 3.5963. Min Act: -0.0000

Data Index: 952089 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 3.5963. Min Range: -3.5963

Max Act: 3.1240. Min Act: -0.0000

Data Index: 1717049 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 3.5963. Min Range: -3.5963

Max Act: 3.1119. Min Act: -0.0000

Data Index: 1009713 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 3.5963. Min Range: -3.5963

Max Act: 3.1834. Min Act: -0.0000

Data Index: 1670324 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 3.5963. Min Range: -3.5963

Max Act: 3.0588. Min Act: -0.0000

Data Index: 344703 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.9257. Min Act: -0.0000

Data Index: 1864410 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1140677 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.8064. Min Act: -0.0000

Data Index: 536982 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.7645. Min Act: -0.0000

Data Index: 311152 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.4563. Min Act: -0.0000

Data Index: 22169 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.4413. Min Act: -0.0000

Data Index: 383751 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5695. Min Act: -0.0000

Data Index: 420060 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5397. Min Act: -0.0000

Data Index: 777031 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5367. Min Act: -0.0000

Data Index: 977578 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.9109. Min Act: -0.0000

Data Index: 562916 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.4941. Min Act: -0.0000

Data Index: 1277512 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.4443. Min Act: -0.0000

Data Index: 842906 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5360. Min Act: -0.0000

Data Index: 134192 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.7505. Min Act: -0.0000

Data Index: 617142 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 3.5963. Min Range: -3.5963

Max Act: 2.5507. Min Act: -0.0000

Data Index: 658679 (The Pile)

Max Activating Token Index: 348