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

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

Neuron 4793 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1507849 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1445253 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1540900 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1549583 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1429857 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1411919 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1576808 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1514100 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1564349 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1510567 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8892. Min Act: -0.0000

Data Index: 936940 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1090539 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1368069 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9364. Min Act: -0.0000

Data Index: 784226 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1558773 (Python Code)

Max Activating Token Index: 445

Text #15

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9133. Min Act: -0.0000

Data Index: 1648859 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1593868 (Python Code)

Max Activating Token Index: 503

Text #17

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1146422 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1631619 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 1.3966. Min Range: -1.3966

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1598954 (Python Code)

Max Activating Token Index: 280