Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2008 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0003

Data Index: 914513 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0969. Min Act: -0.0003

Data Index: 258468 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0907. Min Act: -0.0003

Data Index: 380272 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0830. Min Act: -0.0003

Data Index: 56247 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0779. Min Act: -0.0003

Data Index: 45876 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0776. Min Act: -0.0003

Data Index: 20925 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0756. Min Act: -0.0003

Data Index: 365318 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0752. Min Act: -0.0003

Data Index: 390309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1144393 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0733. Min Act: -0.0003

Data Index: 890376 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0743. Min Act: -0.0003

Data Index: 886169 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0728. Min Act: -0.0003

Data Index: 754669 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1304052 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0710. Min Act: -0.0003

Data Index: 636191 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1293864 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0705. Min Act: -0.0003

Data Index: 1348389 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0745. Min Act: -0.0003

Data Index: 199262 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0712. Min Act: -0.0003

Data Index: 841785 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0699. Min Act: -0.0003

Data Index: 827779 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1105137 (C4 (Web Text))

Max Activating Token Index: 121