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

Dataset: The Pile

Neuron 4830 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: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1159335 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1388322 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0715. Min Act: -0.0000

Data Index: 252675 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1805681 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1833897 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0723. Min Act: -0.0000

Data Index: 406946 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1059642 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1345604 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0638. Min Act: -0.0000

Data Index: 594225 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0646. Min Act: -0.0000

Data Index: 158127 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1360264 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1953533 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0483. Min Act: -0.0000

Data Index: 608904 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0520. Min Act: -0.0000

Data Index: 660518 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1819250 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0465. Min Act: -0.0000

Data Index: 651876 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1411328 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1583010 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1437361 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0512. Min Act: -0.0000

Data Index: 852007 (The Pile)

Max Activating Token Index: 626