Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0001

Data Index: 778567 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1640. Min Act: -0.0001

Data Index: 112371 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1501. Min Act: -0.0002

Data Index: 329177 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1278895 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1388. Min Act: -0.0001

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1376. Min Act: -0.0002

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1347. Min Act: -0.0001

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1278. Min Act: -0.0001

Data Index: 641525 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1322. Min Act: -0.0002

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1271. Min Act: -0.0001

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1325531 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1240. Min Act: -0.0001

Data Index: 935596 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1257. Min Act: -0.0001

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1238. Min Act: -0.0001

Data Index: 508661 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1191. Min Act: -0.0001

Data Index: 179954 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1101137 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1242166 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1234. Min Act: -0.0001

Data Index: 527891 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1139922 (C4 (Web Text))

Max Activating Token Index: 725