Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 25 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1499542 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1608. Min Act: -0.0002

Data Index: 1361907 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1654. Min Act: -0.0002

Data Index: 1499935 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1636683 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1435793 (Python Code)

Max Activating Token Index: 966

Text #5

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1631248 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1550. Min Act: -0.0002

Data Index: 1522227 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1490795 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1567776 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1443593 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1465937 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1621076 (Python Code)

Max Activating Token Index: 915

Text #12

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1618472 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1528. Min Act: -0.0002

Data Index: 1393964 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1614656 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1548060 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1514. Min Act: -0.0002

Data Index: 509569 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1447. Min Act: -0.0002

Data Index: 1570667 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1502. Min Act: -0.0002

Data Index: 741679 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1513. Min Act: -0.0002

Data Index: 1459175 (Python Code)

Max Activating Token Index: 510