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

Dataset: The Pile

Neuron 4681 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: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1514852 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1203511 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1438314 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1922383 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1442. Min Act: -0.0000

Data Index: 891664 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1325737 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1246058 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1959516 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1138953 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1398775 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1925187 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1437. Min Act: -0.0000

Data Index: 774131 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1365615 (The Pile)

Max Activating Token Index: 952

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1391. Min Act: -0.0000

Data Index: 781284 (The Pile)

Max Activating Token Index: 562

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1645129 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1699230 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1522. Min Act: -0.0000

Data Index: 64015 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1407282 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1422. Min Act: -0.0000

Data Index: 495568 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1417. Min Act: -0.0000

Data Index: 36819 (The Pile)

Max Activating Token Index: 763