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

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

Neuron 2918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6910. Min Act: -0.0003

Data Index: 153342 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6462. Min Act: -0.0003

Data Index: 978771 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5983. Min Act: -0.0003

Data Index: 1337595 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6004. Min Act: -0.0003

Data Index: 135085 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6201. Min Act: -0.0003

Data Index: 770051 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5557. Min Act: -0.0002

Data Index: 743149 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5806. Min Act: -0.0003

Data Index: 610149 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5716. Min Act: -0.0003

Data Index: 80137 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5377. Min Act: -0.0003

Data Index: 640469 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5894. Min Act: -0.0003

Data Index: 1267143 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5673. Min Act: -0.0003

Data Index: 865822 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5526. Min Act: -0.0003

Data Index: 886015 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5328. Min Act: -0.0003

Data Index: 896505 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5394. Min Act: -0.0003

Data Index: 926794 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5220. Min Act: -0.0003

Data Index: 907154 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5382. Min Act: -0.0003

Data Index: 53259 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5342. Min Act: -0.0003

Data Index: 354779 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5331. Min Act: -0.0003

Data Index: 604359 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5315. Min Act: -0.0003

Data Index: 1083148 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5104. Min Act: -0.0003

Data Index: 47612 (C4 (Web Text))

Max Activating Token Index: 797