Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1599029 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1623466 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1412067 (Python Code)

Max Activating Token Index: 693

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1498155 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1630313 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1376700 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1401010 (Python Code)

Max Activating Token Index: 618

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1577377 (Python Code)

Max Activating Token Index: 819

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1523155 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1374579 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1396503 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1382618 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1566516 (Python Code)

Max Activating Token Index: 828

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1544969 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1412208 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1381869 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1639366 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1500212 (Python Code)

Max Activating Token Index: 827

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1499330 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1615058 (Python Code)

Max Activating Token Index: 707