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

Dataset: The Pile

Neuron 1458 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: 0.0000

Data Index: 548040 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1411386 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0524. Min Act: 0.0000

Data Index: 1998164 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0522. Min Act: 0.0000

Data Index: 1608100 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0512. Min Act: 0.0000

Data Index: 216088 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0509. Min Act: 0.0000

Data Index: 1588084 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0504. Min Act: -0.0000

Data Index: 791173 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0482. Min Act: 0.0000

Data Index: 1952716 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0515. Min Act: 0.0000

Data Index: 1174950 (The Pile)

Max Activating Token Index: 2

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0512. Min Act: 0.0000

Data Index: 1833912 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0493. Min Act: 0.0000

Data Index: 139003 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0490. Min Act: 0.0000

Data Index: 522564 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0490. Min Act: 0.0000

Data Index: 556380 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0490. Min Act: 0.0000

Data Index: 1236748 (The Pile)

Max Activating Token Index: 288

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0489. Min Act: 0.0000

Data Index: 1402820 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0487. Min Act: 0.0000

Data Index: 1375853 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0487. Min Act: 0.0000

Data Index: 1336939 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0487. Min Act: -0.0000

Data Index: 322549 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1740746 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0485. Min Act: -0.0000

Data Index: 540017 (The Pile)

Max Activating Token Index: 835