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

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

Neuron 4517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1138. Min Range: -7.1138

Max Act: 7.1138. Min Act: -0.0000

Data Index: 1427578 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 7.1138. Min Range: -7.1138

Max Act: 6.7421. Min Act: -0.0000

Data Index: 1601962 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 7.1138. Min Range: -7.1138

Max Act: 6.3229. Min Act: -0.0000

Data Index: 1360213 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.6778. Min Act: -0.0000

Data Index: 1429906 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.4386. Min Act: -0.0000

Data Index: 1544626 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.4172. Min Act: -0.0000

Data Index: 1583736 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.4047. Min Act: -0.0000

Data Index: 1460250 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.2716. Min Act: -0.0000

Data Index: 1504487 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.2622. Min Act: -0.0000

Data Index: 1576954 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.2270. Min Act: -0.0000

Data Index: 1549567 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.1459. Min Act: -0.0000

Data Index: 1509019 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.9644. Min Act: -0.0000

Data Index: 1540993 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.0742. Min Act: -0.0000

Data Index: 1390443 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.0710. Min Act: -0.0000

Data Index: 1571845 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.8179. Min Act: -0.0000

Data Index: 1549161 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.9602. Min Act: -0.0000

Data Index: 1361980 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 7.1138. Min Range: -7.1138

Max Act: 5.1552. Min Act: -0.0000

Data Index: 1570557 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.9271. Min Act: -0.0000

Data Index: 1435301 (Python Code)

Max Activating Token Index: 510

Text #18

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.9132. Min Act: -0.0000

Data Index: 1556840 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 7.1138. Min Range: -7.1138

Max Act: 4.7234. Min Act: -0.0000

Data Index: 1531570 (Python Code)

Max Activating Token Index: 118