Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 278 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0002

Data Index: 771027 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1411. Min Act: -0.0002

Data Index: 498239 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1064456 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1074025 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1421. Min Act: -0.0002

Data Index: 291761 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1463207 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1520577 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1411. Min Act: -0.0002

Data Index: 512144 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1396. Min Act: -0.0002

Data Index: 166578 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1346. Min Act: -0.0002

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1384. Min Act: -0.0002

Data Index: 3625 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1137926 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1323610 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1358. Min Act: -0.0002

Data Index: 229211 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1296. Min Act: -0.0002

Data Index: 117149 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1653993 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1265. Min Act: -0.0002

Data Index: 339498 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1302. Min Act: -0.0002

Data Index: 342714 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1126598 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1263. Min Act: -0.0002

Data Index: 814806 (C4 (Web Text))

Max Activating Token Index: 742