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

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

Neuron 998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.8922. Min Act: -0.0003

Data Index: 1237870 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.8225. Min Act: -0.0003

Data Index: 45329 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.7703. Min Act: -0.0003

Data Index: 874617 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6693. Min Act: -0.0003

Data Index: 1225314 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6912. Min Act: -0.0002

Data Index: 467785 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6549. Min Act: -0.0003

Data Index: 704231 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6691. Min Act: -0.0003

Data Index: 459725 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6795. Min Act: -0.0003

Data Index: 723504 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6572. Min Act: -0.0003

Data Index: 756798 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6460. Min Act: -0.0003

Data Index: 1254028 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6436. Min Act: -0.0002

Data Index: 527269 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6370. Min Act: -0.0003

Data Index: 867801 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6281. Min Act: -0.0003

Data Index: 353867 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6308. Min Act: -0.0002

Data Index: 1211218 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6133. Min Act: -0.0003

Data Index: 988863 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6304. Min Act: -0.0003

Data Index: 953368 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6258. Min Act: -0.0003

Data Index: 637875 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6263. Min Act: -0.0003

Data Index: 1030070 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6206. Min Act: -0.0002

Data Index: 1323182 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.8922. Min Range: -0.8922

Max Act: 0.6161. Min Act: -0.0003

Data Index: 190403 (C4 (Web Text))

Max Activating Token Index: 628