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

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

Neuron 4165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6898. Min Act: -0.0002

Data Index: 975260 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6353. Min Act: -0.0002

Data Index: 1297386 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6332. Min Act: -0.0002

Data Index: 1094985 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6322. Min Act: -0.0002

Data Index: 543705 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6696. Min Act: -0.0002

Data Index: 758039 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6438. Min Act: -0.0002

Data Index: 860672 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6653. Min Act: -0.0002

Data Index: 701359 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6061. Min Act: -0.0002

Data Index: 244102 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6273. Min Act: -0.0002

Data Index: 772817 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6118. Min Act: -0.0002

Data Index: 1335285 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6308. Min Act: -0.0002

Data Index: 1315864 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6228. Min Act: -0.0002

Data Index: 276243 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6198. Min Act: -0.0002

Data Index: 752156 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6153. Min Act: -0.0002

Data Index: 321781 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6547. Min Act: -0.0002

Data Index: 894060 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6065. Min Act: -0.0002

Data Index: 631334 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6145. Min Act: -0.0002

Data Index: 878764 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.6266. Min Act: -0.0002

Data Index: 480184 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.5941. Min Act: -0.0002

Data Index: 1039633 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.6898. Min Range: -0.6898

Max Act: 0.5767. Min Act: -0.0002

Data Index: 1340582 (C4 (Web Text))

Max Activating Token Index: 152