Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1238. Min Range: -3.1238

Max Act: 3.1238. Min Act: -0.0000

Data Index: 1186899 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 3.1238. Min Range: -3.1238

Max Act: 3.0692. Min Act: -0.0000

Data Index: 612883 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.8716. Min Act: -0.0000

Data Index: 245313 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 3.1238. Min Range: -3.1238

Max Act: 3.0373. Min Act: -0.0000

Data Index: 403043 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.8202. Min Act: -0.0000

Data Index: 795555 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.6594. Min Act: -0.0001

Data Index: 328365 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.7658. Min Act: -0.0000

Data Index: 1305660 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.4460. Min Act: -0.0000

Data Index: 147123 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.4178. Min Act: -0.0000

Data Index: 324427 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.5067. Min Act: -0.0000

Data Index: 255477 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.5046. Min Act: -0.0000

Data Index: 958343 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1028542 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.0130. Min Act: -0.0000

Data Index: 318508 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.4823. Min Act: -0.0000

Data Index: 812413 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.3041. Min Act: -0.0000

Data Index: 541142 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.1833. Min Act: -0.0000

Data Index: 746985 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.2478. Min Act: -0.0000

Data Index: 1348702 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.0960. Min Act: -0.0000

Data Index: 271903 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.0873. Min Act: -0.0000

Data Index: 1183555 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 3.1238. Min Range: -3.1238

Max Act: 2.1643. Min Act: -0.0000

Data Index: 1334594 (C4 (Web Text))

Max Activating Token Index: 987