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

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

Neuron 3334 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: 2.2798. Min Range: -2.2798

Max Act: 2.2798. Min Act: -0.0000

Data Index: 362041 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.8549. Min Act: -0.0000

Data Index: 878066 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.5782. Min Act: -0.0000

Data Index: 950618 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.6675. Min Act: -0.0000

Data Index: 478758 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.7339. Min Act: -0.0000

Data Index: 510865 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.6209. Min Act: -0.0000

Data Index: 403239 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1599255 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.4451. Min Act: -0.0000

Data Index: 159320 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.6313. Min Act: -0.0000

Data Index: 1503539 (Python Code)

Max Activating Token Index: 745

Text #9

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.6044. Min Act: -0.0000

Data Index: 704541 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1272986 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.4564. Min Act: -0.0000

Data Index: 1160914 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1123234 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.3387. Min Act: -0.0000

Data Index: 874287 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1573653 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.3005. Min Act: -0.0000

Data Index: 519623 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.2478. Min Act: -0.0000

Data Index: 880004 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.2960. Min Act: -0.0000

Data Index: 469405 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1222420 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 2.2798. Min Range: -2.2798

Max Act: 1.3367. Min Act: -0.0000

Data Index: 743864 (C4 (Web Text))

Max Activating Token Index: 898