Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1488145 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1312840 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1477603 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7726. Min Act: -0.0000

Data Index: 972229 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1761195 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7245. Min Act: -0.0000

Data Index: 767381 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.6557. Min Act: -0.0000

Data Index: 657927 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7167. Min Act: -0.0000

Data Index: 465033 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1225927 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1204255 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1972732 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1915406 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1796855 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1966623 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1906271 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1674115 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.6551. Min Act: -0.0000

Data Index: 165578 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1690402 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.5984. Min Act: -0.0000

Data Index: 844510 (The Pile)

Max Activating Token Index: 530

Text #19

Max Range: 0.8379. Min Range: -0.8379

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1035777 (The Pile)

Max Activating Token Index: 103