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

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

Neuron 3871 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1073357 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1568. Min Act: -0.0000

Data Index: 10365 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1575. Min Act: -0.0001

Data Index: 77969 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1033823 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1319. Min Act: -0.0000

Data Index: 763741 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1358. Min Act: -0.0000

Data Index: 352982 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1193740 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1348. Min Act: -0.0000

Data Index: 974590 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1335. Min Act: -0.0000

Data Index: 15399 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1250378 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1276. Min Act: -0.0000

Data Index: 319805 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1239. Min Act: -0.0000

Data Index: 400021 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1324. Min Act: -0.0001

Data Index: 259162 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1304540 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1195688 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1239. Min Act: -0.0000

Data Index: 625346 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1180772 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1230. Min Act: -0.0001

Data Index: 938262 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1204. Min Act: -0.0000

Data Index: 883362 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1146. Min Act: -0.0000

Data Index: 714214 (C4 (Web Text))

Max Activating Token Index: 210