Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3215 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1632464 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1577347 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2480. Min Act: -0.0000

Data Index: 809866 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1453830 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2398. Min Act: -0.0000

Data Index: 596594 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2468. Min Act: -0.0000

Data Index: 412613 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2420. Min Act: -0.0000

Data Index: 131207 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2285. Min Act: -0.0000

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2221. Min Act: -0.0000

Data Index: 546010 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2051. Min Act: -0.0000

Data Index: 685338 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2142. Min Act: -0.0000

Data Index: 211359 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2523. Min Act: -0.0000

Data Index: 414470 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1763. Min Act: -0.0000

Data Index: 376007 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1440476 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2010. Min Act: -0.0000

Data Index: 712175 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1941. Min Act: -0.0000

Data Index: 502448 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2234. Min Act: -0.0000

Data Index: 863218 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1112872 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1085792 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1063681 (C4 (Web Text))

Max Activating Token Index: 395