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

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

Neuron 4514 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.5949. Min Act: -0.0000

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.4694. Min Act: -0.0000

Data Index: 438421 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.3019. Min Act: -0.0000

Data Index: 193947 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.8875. Min Act: -0.0000

Data Index: 621096 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.8053. Min Act: -0.0000

Data Index: 258387 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.7877. Min Act: -0.0000

Data Index: 578337 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.7580. Min Act: -0.0000

Data Index: 238556 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.7417. Min Act: -0.0000

Data Index: 961835 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.7149. Min Act: -0.0000

Data Index: 336566 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6925. Min Act: -0.0000

Data Index: 421131 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6463. Min Act: -0.0000

Data Index: 239127 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6812. Min Act: -0.0000

Data Index: 782345 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6345. Min Act: -0.0000

Data Index: 951173 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6334. Min Act: -0.0000

Data Index: 881486 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1030294 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1017553 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.6018. Min Act: -0.0000

Data Index: 786342 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.5911. Min Act: -0.0000

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1018841 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.5949. Min Range: -1.5949

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1180934 (C4 (Web Text))

Max Activating Token Index: 239