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

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

Neuron 911 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1794. Min Act: -0.0001

Data Index: 19732 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1265144 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1546. Min Act: -0.0001

Data Index: 848594 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1072528 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1488. Min Act: -0.0001

Data Index: 369695 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1518. Min Act: -0.0001

Data Index: 595078 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1548. Min Act: -0.0001

Data Index: 128436 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1503. Min Act: -0.0001

Data Index: 267579 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1589. Min Act: -0.0001

Data Index: 466409 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1015962 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1332334 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1505. Min Act: -0.0001

Data Index: 327293 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1029822 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1493. Min Act: -0.0001

Data Index: 262554 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1449. Min Act: -0.0001

Data Index: 611466 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1442. Min Act: -0.0001

Data Index: 444876 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1483. Min Act: -0.0001

Data Index: 171437 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1432. Min Act: -0.0001

Data Index: 686559 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1119283 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1433. Min Act: -0.0001

Data Index: 683522 (C4 (Web Text))

Max Activating Token Index: 18