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

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

Neuron 903 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0025. Min Range: -1.0025

Max Act: 1.0025. Min Act: -0.0002

Data Index: 676787 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9603. Min Act: -0.0002

Data Index: 287353 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.9283. Min Act: -0.0002

Data Index: 1266691 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8923. Min Act: -0.0002

Data Index: 1347728 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8889. Min Act: -0.0002

Data Index: 413034 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8827. Min Act: -0.0002

Data Index: 140865 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8424. Min Act: -0.0002

Data Index: 605412 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8238. Min Act: -0.0002

Data Index: 711198 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8393. Min Act: -0.0002

Data Index: 1067634 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8287. Min Act: -0.0002

Data Index: 789673 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8159. Min Act: -0.0002

Data Index: 1129582 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8214. Min Act: -0.0002

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8183. Min Act: -0.0002

Data Index: 1250454 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8005. Min Act: -0.0003

Data Index: 1017153 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.8026. Min Act: -0.0002

Data Index: 341051 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7911. Min Act: -0.0002

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7900. Min Act: -0.0002

Data Index: 868318 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7906. Min Act: -0.0002

Data Index: 506132 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7713. Min Act: -0.0002

Data Index: 659033 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.0025. Min Range: -1.0025

Max Act: 0.7755. Min Act: -0.0002

Data Index: 350207 (C4 (Web Text))

Max Activating Token Index: 748