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

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

Neuron 5029 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1731. Min Act: -0.0003

Data Index: 1317494 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1255177 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1475. Min Act: -0.0002

Data Index: 330123 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1380. Min Act: -0.0002

Data Index: 269186 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1491. Min Act: -0.0003

Data Index: 412880 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1388. Min Act: -0.0003

Data Index: 326684 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1375. Min Act: -0.0002

Data Index: 132977 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1372. Min Act: -0.0002

Data Index: 1301695 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1360. Min Act: -0.0002

Data Index: 454489 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1417. Min Act: -0.0003

Data Index: 482477 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1336. Min Act: -0.0002

Data Index: 81721 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1316. Min Act: -0.0003

Data Index: 294560 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1309. Min Act: -0.0002

Data Index: 206860 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1284. Min Act: -0.0002

Data Index: 706815 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1292. Min Act: -0.0002

Data Index: 205785 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1271. Min Act: -0.0002

Data Index: 48621 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1315. Min Act: -0.0002

Data Index: 876103 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1327394 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1100348 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.1731. Min Range: -0.1731

Max Act: 0.1274. Min Act: -0.0002

Data Index: 957097 (C4 (Web Text))

Max Activating Token Index: 355