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

Dataset: The Pile

Neuron 207 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0000

Data Index: 350873 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1211697 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1601. Min Act: -0.0000

Data Index: 457155 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1548. Min Act: -0.0000

Data Index: 852454 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1594. Min Act: -0.0000

Data Index: 99877 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1516. Min Act: -0.0000

Data Index: 437106 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1508. Min Act: -0.0000

Data Index: 782809 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1979473 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1268127 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1725875 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1575007 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1386. Min Act: -0.0000

Data Index: 720559 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1654955 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1094951 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1389. Min Act: -0.0000

Data Index: 743905 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1382. Min Act: -0.0000

Data Index: 811342 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1605445 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1366. Min Act: -0.0000

Data Index: 429902 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1288. Min Act: -0.0000

Data Index: 169817 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1338. Min Act: -0.0000

Data Index: 265614 (The Pile)

Max Activating Token Index: 796