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

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

Neuron 1696 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1601323 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1500069 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1505332 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0631. Min Act: -0.0000

Data Index: 960671 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1458349 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1641829 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1504246 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1530020 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1599221 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1499427 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1632591 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1640096 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1495924 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1469130 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1614055 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1433408 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1529734 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1477612 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1419816 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1149853 (C4 (Web Text))

Max Activating Token Index: 680