Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1652. Min Act: -0.0002

Data Index: 66975 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1602. Min Act: -0.0002

Data Index: 4307 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1407. Min Act: -0.0002

Data Index: 800353 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1457. Min Act: -0.0002

Data Index: 384990 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1440. Min Act: -0.0002

Data Index: 952860 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1423. Min Act: -0.0002

Data Index: 931794 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1465. Min Act: -0.0002

Data Index: 904009 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1321. Min Act: -0.0002

Data Index: 585353 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1409. Min Act: -0.0002

Data Index: 369749 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1427. Min Act: -0.0002

Data Index: 744719 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1399. Min Act: -0.0002

Data Index: 15982 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1371. Min Act: -0.0002

Data Index: 1337883 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1263652 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1295. Min Act: -0.0002

Data Index: 183840 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1423. Min Act: -0.0002

Data Index: 766803 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1339. Min Act: -0.0002

Data Index: 184609 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1322. Min Act: -0.0002

Data Index: 253242 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1253632 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1265. Min Act: -0.0002

Data Index: 1232738 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1165276 (C4 (Web Text))

Max Activating Token Index: 106