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

Dataset: The Pile

Neuron 2612 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: 1.4281. Min Range: -1.4281

Max Act: 1.4281. Min Act: -0.0000

Data Index: 536341 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1427043 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.3275. Min Act: -0.0000

Data Index: 738427 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1376614 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.1601. Min Act: -0.0000

Data Index: 2050 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1140579 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.1263. Min Act: -0.0000

Data Index: 1072666 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.0165. Min Act: -0.0000

Data Index: 655634 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1252035 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.4281. Min Range: -1.4281

Max Act: 1.0844. Min Act: -0.0000

Data Index: 421474 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1952444 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1863760 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.8106. Min Act: -0.0000

Data Index: 765001 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1255902 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.7674. Min Act: -0.0000

Data Index: 219497 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1032476 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.7679. Min Act: -0.0000

Data Index: 403089 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1076467 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.7920. Min Act: -0.0000

Data Index: 444204 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 1.4281. Min Range: -1.4281

Max Act: 0.6688. Min Act: -0.0000

Data Index: 474882 (The Pile)

Max Activating Token Index: 933