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

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

Neuron 5094 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: 0.1679. Min Range: -0.1679

Max Act: 0.1679. Min Act: -0.0002

Data Index: 788553 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1584. Min Act: -0.0002

Data Index: 723826 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1518. Min Act: -0.0002

Data Index: 256753 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1277049 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1346. Min Act: -0.0002

Data Index: 167103 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1395. Min Act: -0.0002

Data Index: 680521 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1369. Min Act: -0.0002

Data Index: 65724 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1357. Min Act: -0.0002

Data Index: 1188987 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1258. Min Act: -0.0002

Data Index: 211201 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1343. Min Act: -0.0002

Data Index: 86633 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1254. Min Act: -0.0002

Data Index: 583757 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1232. Min Act: -0.0002

Data Index: 338008 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1272. Min Act: -0.0002

Data Index: 676745 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1202. Min Act: -0.0002

Data Index: 574062 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1201. Min Act: -0.0002

Data Index: 647760 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1172465 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1089816 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1184853 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1168. Min Act: -0.0002

Data Index: 146311 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.1679. Min Range: -0.1679

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1060750 (C4 (Web Text))

Max Activating Token Index: 763