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

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

Neuron 5337 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1234. Min Range: -1.1234

Max Act: 1.1234. Min Act: -0.0001

Data Index: 1534715 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 1.1234. Min Range: -1.1234

Max Act: 1.0227. Min Act: -0.0001

Data Index: 1374564 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1513413 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9641. Min Act: -0.0001

Data Index: 1462866 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8948. Min Act: -0.0001

Data Index: 1495916 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8553. Min Act: -0.0001

Data Index: 1613032 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1408766 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1471620 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1582894 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8557. Min Act: -0.0001

Data Index: 1440453 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1626809 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1361359 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1463684 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1630195 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1606293 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1360592 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1426565 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7377. Min Act: -0.0001

Data Index: 1620751 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1417279 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.1234. Min Range: -1.1234

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1443736 (Python Code)

Max Activating Token Index: 829