Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2440 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.2126. Min Act: -0.0003

Data Index: 802572 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1953. Min Act: -0.0003

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1688. Min Act: -0.0003

Data Index: 1267177 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1883. Min Act: -0.0003

Data Index: 977127 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1886. Min Act: -0.0003

Data Index: 333438 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1848. Min Act: -0.0003

Data Index: 1264695 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1847. Min Act: -0.0003

Data Index: 11556 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1695. Min Act: -0.0003

Data Index: 379844 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1728. Min Act: -0.0003

Data Index: 1063526 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1642. Min Act: -0.0003

Data Index: 1103637 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1816. Min Act: -0.0003

Data Index: 580238 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1676. Min Act: -0.0003

Data Index: 1258371 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1681. Min Act: -0.0003

Data Index: 1107996 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1740. Min Act: -0.0003

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1608. Min Act: -0.0003

Data Index: 575849 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1710. Min Act: -0.0003

Data Index: 385659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1784. Min Act: -0.0003

Data Index: 702087 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1714. Min Act: -0.0003

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1647. Min Act: -0.0003

Data Index: 1314535 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1766. Min Act: -0.0003

Data Index: 819322 (C4 (Web Text))

Max Activating Token Index: 108