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

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

Neuron 1214 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: 0.1743. Min Range: -0.1743

Max Act: 0.1732. Min Act: -0.0002

Data Index: 1181883 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1444. Min Act: -0.0002

Data Index: 1617924 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1661. Min Act: -0.0002

Data Index: 960268 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1446266 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1552. Min Act: -0.0002

Data Index: 291826 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1743. Min Act: -0.0002

Data Index: 1393810 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1649334 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1456. Min Act: -0.0002

Data Index: 391920 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1616. Min Act: -0.0002

Data Index: 986103 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1280. Min Act: -0.0002

Data Index: 1464448 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1328. Min Act: -0.0002

Data Index: 878475 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1452973 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1407. Min Act: -0.0002

Data Index: 955188 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1565836 (Python Code)

Max Activating Token Index: 932

Text #14

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1549453 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1125861 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1284. Min Act: -0.0003

Data Index: 1567181 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1388139 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1176686 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.1743. Min Range: -0.1743

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1501390 (Python Code)

Max Activating Token Index: 917