Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1609. Min Act: -0.0001

Data Index: 350043 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1491. Min Act: -0.0001

Data Index: 918945 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1227762 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1406. Min Act: -0.0001

Data Index: 857537 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1201761 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1320791 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1086710 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1446. Min Act: -0.0001

Data Index: 353875 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1323. Min Act: -0.0001

Data Index: 921215 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1139. Min Act: -0.0001

Data Index: 973583 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1313. Min Act: -0.0001

Data Index: 233821 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1251. Min Act: -0.0001

Data Index: 866972 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1303. Min Act: -0.0001

Data Index: 62475 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1222. Min Act: -0.0001

Data Index: 247005 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1253. Min Act: -0.0001

Data Index: 362802 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1197. Min Act: -0.0001

Data Index: 728716 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1246. Min Act: -0.0001

Data Index: 176945 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1197. Min Act: -0.0001

Data Index: 304535 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1131. Min Act: -0.0001

Data Index: 605006 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.1609. Min Range: -0.1609

Max Act: 0.1253. Min Act: -0.0001

Data Index: 160222 (C4 (Web Text))

Max Activating Token Index: 40