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

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

Neuron 1206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1696. Min Act: -0.0000

Data Index: 726413 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1719. Min Act: -0.0000

Data Index: 422306 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1846. Min Act: -0.0000

Data Index: 529914 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1375. Min Act: -0.0000

Data Index: 181660 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1382. Min Act: -0.0000

Data Index: 232359 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1220110 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1345. Min Act: -0.0000

Data Index: 479935 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1613845 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1204. Min Act: -0.0000

Data Index: 910421 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1288216 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1245. Min Act: -0.0000

Data Index: 307099 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1198. Min Act: -0.0000

Data Index: 971178 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1102. Min Act: -0.0000

Data Index: 982583 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1206. Min Act: -0.0000

Data Index: 470718 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1186. Min Act: -0.0000

Data Index: 561386 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1224. Min Act: -0.0000

Data Index: 485386 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1184. Min Act: -0.0000

Data Index: 434327 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1387. Min Act: -0.0000

Data Index: 465040 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1258547 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.1846. Min Range: -0.1846

Max Act: 0.0998. Min Act: -0.0000

Data Index: 889819 (C4 (Web Text))

Max Activating Token Index: 942