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

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

Neuron 2868 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1453830 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1632464 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3012. Min Act: -0.0000

Data Index: 984196 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.3028. Min Act: -0.0000

Data Index: 463527 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2776. Min Act: -0.0000

Data Index: 394951 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2558. Min Act: -0.0000

Data Index: 897665 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2552. Min Act: -0.0000

Data Index: 139742 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2589. Min Act: -0.0000

Data Index: 589633 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2436. Min Act: -0.0000

Data Index: 651119 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2523. Min Act: -0.0000

Data Index: 175716 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1227404 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2260. Min Act: -0.0000

Data Index: 330795 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2374. Min Act: -0.0000

Data Index: 701122 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1618815 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1577347 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2402. Min Act: -0.0000

Data Index: 218378 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2242. Min Act: 0.0001

Data Index: 1109573 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1313496 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2200. Min Act: -0.0000

Data Index: 172234 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.3059. Min Range: -0.3059

Max Act: 0.2313. Min Act: -0.0000

Data Index: 47808 (C4 (Web Text))

Max Activating Token Index: 546