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

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

Neuron 438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0825. Min Range: -2.0825

Max Act: 2.0825. Min Act: -0.0000

Data Index: 703487 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.9187. Min Act: -0.0000

Data Index: 190936 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.8494. Min Act: -0.0000

Data Index: 710961 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6908. Min Act: -0.0000

Data Index: 182717 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.8368. Min Act: -0.0000

Data Index: 409759 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6196. Min Act: -0.0000

Data Index: 327139 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6738. Min Act: -0.0000

Data Index: 273803 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6629. Min Act: -0.0000

Data Index: 298966 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.5476. Min Act: -0.0000

Data Index: 829684 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4678. Min Act: -0.0000

Data Index: 946157 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.5419. Min Act: -0.0000

Data Index: 511712 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1173830 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4749. Min Act: -0.0000

Data Index: 446055 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4725. Min Act: -0.0000

Data Index: 38670 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4759. Min Act: -0.0000

Data Index: 250244 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1275301 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4333. Min Act: -0.0000

Data Index: 626303 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4124. Min Act: -0.0000

Data Index: 811395 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1150308 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4160. Min Act: -0.0000

Data Index: 689526 (C4 (Web Text))

Max Activating Token Index: 231