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

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

Neuron 4712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 809694 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2368. Min Act: -0.0000

Data Index: 966707 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1311144 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2254. Min Act: -0.0000

Data Index: 838760 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1939. Min Act: -0.0000

Data Index: 65795 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1765. Min Act: -0.0000

Data Index: 202552 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1728. Min Act: -0.0000

Data Index: 669709 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1094668 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1468. Min Act: -0.0000

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1460. Min Act: -0.0000

Data Index: 987274 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1284464 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1543154 (Python Code)

Max Activating Token Index: 669

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1352. Min Act: -0.0001

Data Index: 148904 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1337. Min Act: -0.0001

Data Index: 573079 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1270. Min Act: -0.0000

Data Index: 853806 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1363. Min Act: -0.0000

Data Index: 353793 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1263. Min Act: -0.0000

Data Index: 852511 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1428. Min Act: -0.0000

Data Index: 156714 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1169270 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1465861 (Python Code)

Max Activating Token Index: 354