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

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

Neuron 1800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1550. Min Act: -0.0003

Data Index: 87081 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1471. Min Act: -0.0003

Data Index: 1136973 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0003

Data Index: 204591 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1426. Min Act: -0.0003

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1417. Min Act: -0.0003

Data Index: 1050213 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1343. Min Act: -0.0003

Data Index: 131829 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1311. Min Act: -0.0003

Data Index: 1059383 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1398. Min Act: -0.0003

Data Index: 455730 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1410. Min Act: -0.0003

Data Index: 1359313 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1243. Min Act: -0.0003

Data Index: 598176 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1309. Min Act: -0.0003

Data Index: 1159985 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1237. Min Act: -0.0003

Data Index: 74927 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1259. Min Act: -0.0003

Data Index: 621656 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1316. Min Act: -0.0003

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1306. Min Act: -0.0003

Data Index: 1317859 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1265. Min Act: -0.0003

Data Index: 207461 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1301. Min Act: -0.0003

Data Index: 249222 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1287056 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1363. Min Act: -0.0003

Data Index: 1006632 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1257. Min Act: -0.0003

Data Index: 295856 (C4 (Web Text))

Max Activating Token Index: 241