Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 942 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0001

Data Index: 520114 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1387. Min Act: -0.0001

Data Index: 393898 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1376. Min Act: -0.0001

Data Index: 48939 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1015343 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1307. Min Act: -0.0001

Data Index: 999887 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1265. Min Act: -0.0001

Data Index: 626366 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1281. Min Act: -0.0001

Data Index: 596175 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1368. Min Act: -0.0001

Data Index: 135025 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1257. Min Act: -0.0001

Data Index: 986470 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1341422 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1006173 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1265. Min Act: -0.0001

Data Index: 742727 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1215. Min Act: -0.0001

Data Index: 53660 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1224. Min Act: -0.0001

Data Index: 970649 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1344. Min Act: -0.0001

Data Index: 206815 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1292. Min Act: -0.0001

Data Index: 112748 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1287. Min Act: -0.0001

Data Index: 389412 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1256029 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1196. Min Act: -0.0001

Data Index: 100583 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1248. Min Act: -0.0001

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 747