Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0002

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1467. Min Act: -0.0002

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1356. Min Act: -0.0002

Data Index: 536388 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1457. Min Act: -0.0002

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1283. Min Act: -0.0002

Data Index: 573195 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1215. Min Act: -0.0002

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1230. Min Act: -0.0002

Data Index: 222099 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1128. Min Act: -0.0002

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1167. Min Act: -0.0002

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1299. Min Act: -0.0002

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1120. Min Act: -0.0002

Data Index: 350958 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1192. Min Act: -0.0002

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1106. Min Act: -0.0002

Data Index: 598341 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1075. Min Act: -0.0002

Data Index: 770257 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1168. Min Act: -0.0002

Data Index: 1360371 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1127. Min Act: -0.0002

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1055. Min Act: -0.0002

Data Index: 266860 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1094. Min Act: -0.0002

Data Index: 362908 (C4 (Web Text))

Max Activating Token Index: 543