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

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

Neuron 1658 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6022. Min Range: -4.6022

Max Act: 4.4106. Min Act: -0.0000

Data Index: 1010919 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 4.6022. Min Range: -4.6022

Max Act: 4.6022. Min Act: -0.0000

Data Index: 556812 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.4431. Min Act: -0.0000

Data Index: 1129861 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.7399. Min Act: -0.0000

Data Index: 682865 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.6793. Min Act: -0.0000

Data Index: 902359 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.3908. Min Act: -0.0000

Data Index: 531091 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.5622. Min Act: -0.0000

Data Index: 1054507 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.5737. Min Act: -0.0000

Data Index: 327861 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.1332. Min Act: -0.0000

Data Index: 1348128 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.5789. Min Act: -0.0000

Data Index: 420007 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.4806. Min Act: -0.0000

Data Index: 779641 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.4296. Min Act: -0.0000

Data Index: 428547 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.6271. Min Act: -0.0000

Data Index: 847566 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.1102. Min Act: -0.0000

Data Index: 1278149 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.4056. Min Act: -0.0000

Data Index: 1324832 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.2194. Min Act: -0.0000

Data Index: 536183 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.3678. Min Act: -0.0000

Data Index: 3019 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 4.6022. Min Range: -4.6022

Max Act: 2.9714. Min Act: -0.0000

Data Index: 873295 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 4.6022. Min Range: -4.6022

Max Act: 3.0801. Min Act: -0.0000

Data Index: 1350020 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 4.6022. Min Range: -4.6022

Max Act: 2.2989. Min Act: -0.0000

Data Index: 801798 (C4 (Web Text))

Max Activating Token Index: 645