Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1790. Min Act: -0.0003

Data Index: 1184706 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1629. Min Act: -0.0002

Data Index: 1204201 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1606. Min Act: -0.0003

Data Index: 1205817 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1593. Min Act: -0.0003

Data Index: 540989 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1258600 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1443. Min Act: -0.0002

Data Index: 368674 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1426. Min Act: -0.0002

Data Index: 492237 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1420. Min Act: -0.0002

Data Index: 22850 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1434. Min Act: -0.0002

Data Index: 1181125 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1435. Min Act: -0.0003

Data Index: 949141 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1392. Min Act: -0.0002

Data Index: 944343 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1440. Min Act: -0.0003

Data Index: 1225503 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1141781 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1363. Min Act: -0.0002

Data Index: 253018 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1391. Min Act: -0.0002

Data Index: 194730 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1390. Min Act: -0.0002

Data Index: 1130206 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1366. Min Act: -0.0002

Data Index: 939618 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1339. Min Act: -0.0002

Data Index: 112629 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1333. Min Act: -0.0002

Data Index: 332415 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.1790. Min Range: -0.1790

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1108800 (C4 (Web Text))

Max Activating Token Index: 384