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

Dataset: The Pile

Neuron 401 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1859248 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1774249 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1875734 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1476. Min Act: -0.0000

Data Index: 553268 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1500. Min Act: -0.0000

Data Index: 616322 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1472. Min Act: -0.0000

Data Index: 793402 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1769007 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1059583 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1384. Min Act: -0.0000

Data Index: 534326 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1012000 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1671485 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1386. Min Act: -0.0000

Data Index: 239906 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1183703 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1857493 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1031238 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1539492 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1608118 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1185988 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1316. Min Act: -0.0000

Data Index: 548173 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1902655 (The Pile)

Max Activating Token Index: 83