Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4957 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6675. Min Act: -0.0000

Data Index: 483063 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6581. Min Act: -0.0000

Data Index: 257456 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5623. Min Act: -0.0000

Data Index: 659848 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1210333 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1240726 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5302. Min Act: -0.0000

Data Index: 546457 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5306. Min Act: -0.0000

Data Index: 642774 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5121. Min Act: -0.0000

Data Index: 141415 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5037. Min Act: -0.0000

Data Index: 226686 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5047. Min Act: -0.0000

Data Index: 49604 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4928. Min Act: -0.0000

Data Index: 783141 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4883. Min Act: -0.0000

Data Index: 88504 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4540. Min Act: -0.0000

Data Index: 920692 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1138535 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4740. Min Act: -0.0000

Data Index: 541293 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1203562 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4416. Min Act: -0.0000

Data Index: 24985 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4332. Min Act: -0.0000

Data Index: 533922 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1079648 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4421. Min Act: -0.0000

Data Index: 124828 (C4 (Web Text))

Max Activating Token Index: 301