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

Dataset: The Pile

Neuron 3999 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: 0.1927. Min Range: -0.1927

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1290290 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1163505 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1742. Min Act: -0.0000

Data Index: 910916 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1527. Min Act: -0.0000

Data Index: 809125 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1486396 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1054909 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1887407 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1987069 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1400. Min Act: -0.0000

Data Index: 910148 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1869193 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1429625 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1416. Min Act: -0.0000

Data Index: 575537 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1244. Min Act: -0.0000

Data Index: 421519 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1150. Min Act: -0.0000

Data Index: 615575 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1785089 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1374. Min Act: 0.0000

Data Index: 71575 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1639241 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1358. Min Act: 0.0000

Data Index: 63853 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1305. Min Act: -0.0000

Data Index: 681660 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 0.1927. Min Range: -0.1927

Max Act: 0.1295. Min Act: -0.0000

Data Index: 308146 (The Pile)

Max Activating Token Index: 696