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

Dataset: The Pile

Neuron 4329 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2468. Min Act: -0.0000

Data Index: 664066 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1073639 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1620. Min Act: -0.0000

Data Index: 562140 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1068661 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1880992 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1546. Min Act: 0.0000

Data Index: 543205 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1452. Min Act: -0.0000

Data Index: 355258 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1441. Min Act: -0.0000

Data Index: 657170 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1683482 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1043857 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1379. Min Act: -0.0000

Data Index: 689335 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1452. Min Act: -0.0000

Data Index: 712679 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1374150 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1560. Min Act: -0.0000

Data Index: 59603 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1366. Min Act: -0.0000

Data Index: 459417 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1976404 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1156005 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1316. Min Act: -0.0000

Data Index: 734937 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1819519 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1222. Min Act: -0.0000

Data Index: 339809 (The Pile)

Max Activating Token Index: 198