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

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

Neuron 1869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1231582 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0996. Min Act: -0.0001

Data Index: 501163 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1028870 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0887. Min Act: -0.0001

Data Index: 992188 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0856. Min Act: -0.0001

Data Index: 197169 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1305043 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1300049 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0889. Min Act: -0.0001

Data Index: 213975 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1231932 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0810. Min Act: -0.0001

Data Index: 540820 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0801. Min Act: -0.0001

Data Index: 751026 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0823. Min Act: -0.0001

Data Index: 87247 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1343399 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1222827 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0793. Min Act: -0.0001

Data Index: 142709 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1145168 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1536585 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0824. Min Act: -0.0001

Data Index: 72974 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0840. Min Act: -0.0001

Data Index: 495891 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0829. Min Act: -0.0001

Data Index: 4021 (C4 (Web Text))

Max Activating Token Index: 995