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

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

Neuron 2973 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1030875 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1196045 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1079672 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8430. Min Act: -0.0000

Data Index: 556690 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8085. Min Act: -0.0000

Data Index: 870055 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8322. Min Act: -0.0000

Data Index: 215711 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8423. Min Act: -0.0000

Data Index: 432925 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8269. Min Act: -0.0000

Data Index: 590065 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1255868 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1150196 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7626. Min Act: -0.0000

Data Index: 633256 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7337. Min Act: -0.0000

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8056. Min Act: -0.0000

Data Index: 643865 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7804. Min Act: -0.0000

Data Index: 716726 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7800. Min Act: -0.0000

Data Index: 672238 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8239. Min Act: -0.0000

Data Index: 587328 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7775. Min Act: -0.0000

Data Index: 85845 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.8224. Min Act: -0.0000

Data Index: 909665 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1033024 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.9243. Min Range: -0.9243

Max Act: 0.7914. Min Act: -0.0000

Data Index: 649844 (C4 (Web Text))

Max Activating Token Index: 893