Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2022 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1385901 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1676. Min Act: -0.0003

Data Index: 1541588 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1656. Min Act: -0.0002

Data Index: 1429577 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1648. Min Act: -0.0002

Data Index: 1489843 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1688. Min Act: -0.0002

Data Index: 1508394 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1578790 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1588. Min Act: -0.0003

Data Index: 1600422 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1577. Min Act: -0.0003

Data Index: 1371867 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1505. Min Act: -0.0003

Data Index: 1364040 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1576. Min Act: -0.0002

Data Index: 1457366 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1585. Min Act: -0.0003

Data Index: 1537662 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1546. Min Act: -0.0002

Data Index: 1457001 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1493. Min Act: -0.0003

Data Index: 1623262 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1592218 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1653875 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1542. Min Act: -0.0002

Data Index: 1567994 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1558. Min Act: -0.0003

Data Index: 1551370 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1490. Min Act: -0.0003

Data Index: 1620836 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1371517 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.1702. Min Range: -0.1702

Max Act: 0.1429. Min Act: -0.0003

Data Index: 1393774 (Python Code)

Max Activating Token Index: 34