Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 530 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.5934. Min Act: -0.0002

Data Index: 516016 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7770. Min Act: -0.0002

Data Index: 639586 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7912. Min Act: -0.0001

Data Index: 128085 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7236. Min Act: -0.0002

Data Index: 1253169 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.5280. Min Act: -0.0002

Data Index: 931432 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.8699. Min Act: -0.0002

Data Index: 1285143 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.8370. Min Act: -0.0002

Data Index: 723175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7211. Min Act: -0.0002

Data Index: 592281 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.5821. Min Act: -0.0002

Data Index: 840392 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6157. Min Act: -0.0001

Data Index: 927852 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6234. Min Act: -0.0002

Data Index: 1293812 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7013. Min Act: -0.0002

Data Index: 975706 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6837. Min Act: -0.0002

Data Index: 680301 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.8049. Min Act: -0.0002

Data Index: 1272728 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.4250. Min Act: -0.0002

Data Index: 72551 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7317. Min Act: -0.0001

Data Index: 1014221 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6128. Min Act: -0.0002

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6734. Min Act: -0.0002

Data Index: 874506 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.7542. Min Act: -0.0001

Data Index: 1237110 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.8699. Min Range: -1.8699

Max Act: 1.6882. Min Act: -0.0002

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 89