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

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

Neuron 2715 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.7263. Min Act: -0.0002

Data Index: 528343 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.7091. Min Act: -0.0002

Data Index: 1178410 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5601. Min Act: -0.0002

Data Index: 415018 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.5801. Min Act: -0.0002

Data Index: 1217115 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.4157. Min Act: -0.0002

Data Index: 51486 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.6021. Min Act: -0.0002

Data Index: 740671 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.1380. Min Act: -0.0002

Data Index: 1313872 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2165. Min Act: -0.0002

Data Index: 1133917 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2733. Min Act: -0.0002

Data Index: 511981 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.0630. Min Act: -0.0002

Data Index: 766111 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3379. Min Act: -0.0002

Data Index: 426291 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2563. Min Act: -0.0002

Data Index: 614146 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.3000. Min Act: -0.0002

Data Index: 16976 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2282. Min Act: -0.0002

Data Index: 1152979 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.1693. Min Act: -0.0002

Data Index: 393864 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.1628. Min Act: -0.0002

Data Index: 157338 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2227. Min Act: -0.0002

Data Index: 1347216 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.2750. Min Act: -0.0002

Data Index: 246596 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.0007. Min Act: -0.0002

Data Index: 448011 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.7263. Min Range: -1.7263

Max Act: 1.1301. Min Act: -0.0002

Data Index: 411665 (C4 (Web Text))

Max Activating Token Index: 797