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

Dataset: The Pile

Neuron 462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1659. Min Act: -0.0000

Data Index: 907611 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1526. Min Act: -0.0000

Data Index: 514410 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1586. Min Act: -0.0000

Data Index: 986314 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1393. Min Act: -0.0000

Data Index: 72703 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1433. Min Act: -0.0000

Data Index: 24328 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1109385 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1601683 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1407. Min Act: -0.0000

Data Index: 271463 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1399573 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1219. Min Act: -0.0000

Data Index: 118414 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1251. Min Act: -0.0000

Data Index: 561210 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1319. Min Act: -0.0000

Data Index: 532951 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1853430 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1055. Min Act: -0.0000

Data Index: 374134 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1598181 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1988895 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1260. Min Act: -0.0000

Data Index: 168495 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1129771 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1105076 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.1659. Min Range: -0.1659

Max Act: 0.1187. Min Act: -0.0000

Data Index: 150847 (The Pile)

Max Activating Token Index: 169