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

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

Neuron 3471 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1141208 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1229508 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.1017. Min Act: -0.0001

Data Index: 200279 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0997. Min Act: -0.0001

Data Index: 405087 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1279213 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0882. Min Act: -0.0001

Data Index: 63228 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0904. Min Act: -0.0001

Data Index: 894034 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0924. Min Act: -0.0001

Data Index: 436289 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0854. Min Act: -0.0001

Data Index: 237794 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0831. Min Act: -0.0001

Data Index: 921680 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0955. Min Act: -0.0001

Data Index: 236508 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0893. Min Act: -0.0001

Data Index: 891296 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0977. Min Act: -0.0001

Data Index: 359654 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1063298 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0720. Min Act: -0.0001

Data Index: 226887 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0671. Min Act: -0.0001

Data Index: 422750 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0740. Min Act: -0.0001

Data Index: 227363 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0758. Min Act: -0.0001

Data Index: 890144 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0753. Min Act: -0.0001

Data Index: 377176 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.1344. Min Range: -0.1344

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1347596 (C4 (Web Text))

Max Activating Token Index: 489