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

Dataset: The Pile

Neuron 3495 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1836645 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6652. Min Act: -0.0000

Data Index: 36779 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1531698 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6202. Min Act: -0.0000

Data Index: 427012 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1197762 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1386395 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1993343 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.6094. Min Act: -0.0000

Data Index: 84344 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5624. Min Act: -0.0000

Data Index: 775338 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5298. Min Act: -0.0000

Data Index: 596622 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5485. Min Act: 0.0000

Data Index: 1986530 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.4957. Min Act: -0.0000

Data Index: 453516 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.4772. Min Act: 0.0000

Data Index: 1654377 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1164433 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5006. Min Act: 0.0000

Data Index: 412050 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5382. Min Act: 0.0000

Data Index: 1505664 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1592988 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.4871. Min Act: 0.0000

Data Index: 1491784 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1204101 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.6982. Min Range: -0.6982

Max Act: 0.4756. Min Act: -0.0000

Data Index: 73659 (The Pile)

Max Activating Token Index: 39