Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1398828 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1527375 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2026. Min Act: -0.0000

Data Index: 881076 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1562721 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1392298 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1841. Min Act: -0.0000

Data Index: 424545 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1470631 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1837. Min Act: -0.0000

Data Index: 345554 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1059111 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1682. Min Act: -0.0000

Data Index: 82006 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1551917 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1754. Min Act: -0.0000

Data Index: 363717 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1690. Min Act: -0.0001

Data Index: 298852 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1170372 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1682. Min Act: -0.0000

Data Index: 717368 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1722. Min Act: -0.0001

Data Index: 400497 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1393036 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1367684 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1607101 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1506196 (Python Code)

Max Activating Token Index: 936