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

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

Neuron 3110 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: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0001

Data Index: 655649 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1321043 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1417. Min Act: -0.0000

Data Index: 185052 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1465. Min Act: -0.0001

Data Index: 580538 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1331265 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1454. Min Act: -0.0000

Data Index: 795055 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1174898 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1355. Min Act: -0.0001

Data Index: 728201 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1388. Min Act: -0.0001

Data Index: 788045 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1332. Min Act: -0.0001

Data Index: 901843 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1215494 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1295. Min Act: -0.0001

Data Index: 40846 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1284. Min Act: -0.0000

Data Index: 918484 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1049169 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1048765 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1265. Min Act: -0.0001

Data Index: 520280 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1242271 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1224. Min Act: -0.0000

Data Index: 212647 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1241243 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1207412 (C4 (Web Text))

Max Activating Token Index: 420