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

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

Neuron 4334 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: 1.9785. Min Range: -1.9785

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1591488 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.9785. Min Act: -0.0000

Data Index: 1606390 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.8112. Min Act: -0.0000

Data Index: 1376896 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.7403. Min Act: -0.0000

Data Index: 1446989 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.7353. Min Act: -0.0000

Data Index: 1548679 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1605619 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.6272. Min Act: -0.0000

Data Index: 1611218 (Python Code)

Max Activating Token Index: 477

Text #7

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.5314. Min Act: 0.0000

Data Index: 1380976 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1632937 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1572894 (Python Code)

Max Activating Token Index: 845

Text #10

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1459942 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.4247. Min Act: 0.0000

Data Index: 1582668 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1455507 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1499726 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1484397 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.3850. Min Act: 0.0000

Data Index: 1399352 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1597562 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.2493. Min Act: 0.0000

Data Index: 1623076 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1397180 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 1.9785. Min Range: -1.9785

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1632816 (Python Code)

Max Activating Token Index: 538