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

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

Neuron 3243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.7368. Min Act: -0.0000

Data Index: 95698 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.6021. Min Act: -0.0000

Data Index: 512994 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.6980. Min Act: -0.0000

Data Index: 797000 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.2919. Min Act: -0.0000

Data Index: 1277581 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1639828 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.4473. Min Act: -0.0000

Data Index: 1328390 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0805. Min Act: -0.0000

Data Index: 276983 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1521235 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1384808 (Python Code)

Max Activating Token Index: 203

Text #9

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0775. Min Act: -0.0000

Data Index: 305257 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0218. Min Act: -0.0000

Data Index: 1401907 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 2.7368. Min Range: -2.7368

Max Act: 1.9857. Min Act: -0.0000

Data Index: 1194930 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.2007. Min Act: -0.0000

Data Index: 1020988 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0847. Min Act: -0.0000

Data Index: 721030 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 2.7368. Min Range: -2.7368

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1355336 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1545014 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.1107. Min Act: -0.0000

Data Index: 165766 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.7368. Min Range: -2.7368

Max Act: 1.8972. Min Act: -0.0000

Data Index: 874953 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.1037. Min Act: -0.0000

Data Index: 70916 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.7368. Min Range: -2.7368

Max Act: 2.1028. Min Act: -0.0000

Data Index: 1115797 (C4 (Web Text))

Max Activating Token Index: 118