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

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

Neuron 3079 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0436. Min Range: -1.0436

Max Act: 1.0021. Min Act: -0.0002

Data Index: 943762 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.0436. Min Range: -1.0436

Max Act: 1.0436. Min Act: -0.0002

Data Index: 119875 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.0436. Min Range: -1.0436

Max Act: 1.0361. Min Act: -0.0002

Data Index: 1056223 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.0436. Min Range: -1.0436

Max Act: 1.0281. Min Act: -0.0002

Data Index: 905776 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9854. Min Act: -0.0002

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9517. Min Act: -0.0002

Data Index: 684579 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.0436. Min Range: -1.0436

Max Act: 1.0171. Min Act: -0.0002

Data Index: 130699 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9518. Min Act: -0.0002

Data Index: 905056 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9423. Min Act: -0.0002

Data Index: 562274 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9338. Min Act: -0.0002

Data Index: 343265 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.8782. Min Act: -0.0002

Data Index: 750470 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9510. Min Act: -0.0002

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9184. Min Act: -0.0002

Data Index: 1162195 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9748. Min Act: -0.0001

Data Index: 846253 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9190. Min Act: -0.0002

Data Index: 448835 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.8842. Min Act: -0.0002

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9636. Min Act: -0.0002

Data Index: 857986 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9467. Min Act: -0.0002

Data Index: 727087 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9405. Min Act: -0.0002

Data Index: 1300752 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.0436. Min Range: -1.0436

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 419