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

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

Neuron 3947 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0002

Data Index: 238046 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1443. Min Act: -0.0002

Data Index: 56323 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1035785 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1410. Min Act: -0.0002

Data Index: 276829 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1405. Min Act: -0.0002

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1392. Min Act: -0.0002

Data Index: 681633 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1368. Min Act: -0.0002

Data Index: 96694 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1366. Min Act: -0.0002

Data Index: 1193356 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1316. Min Act: -0.0002

Data Index: 838029 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1219054 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1330. Min Act: -0.0002

Data Index: 334200 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1284. Min Act: -0.0002

Data Index: 838114 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1328. Min Act: -0.0002

Data Index: 172879 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1323. Min Act: -0.0002

Data Index: 741059 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1003399 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1064461 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1094253 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1292. Min Act: -0.0003

Data Index: 1095084 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1221890 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1251. Min Act: -0.0002

Data Index: 743686 (C4 (Web Text))

Max Activating Token Index: 241