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

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

Neuron 1957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1586599 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1888. Min Act: -0.0001

Data Index: 153400 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1075240 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1389. Min Act: -0.0001

Data Index: 765519 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1553342 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1422. Min Act: -0.0001

Data Index: 31824 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1346. Min Act: -0.0001

Data Index: 397003 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1495675 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1567. Min Act: -0.0001

Data Index: 545000 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1374. Min Act: -0.0001

Data Index: 641619 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1246. Min Act: -0.0001

Data Index: 871521 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1041118 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1179. Min Act: -0.0001

Data Index: 260024 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1386. Min Act: -0.0001

Data Index: 290318 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1424. Min Act: -0.0001

Data Index: 725334 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1164988 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1329741 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1303. Min Act: -0.0001

Data Index: 191975 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1341. Min Act: -0.0001

Data Index: 828902 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.3245. Min Range: -0.3245

Max Act: 0.1417. Min Act: -0.0001

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 188