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

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

Neuron 450 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: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1531939 (Python Code)

Max Activating Token Index: 488

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1489036 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1655517 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1475975 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1539490 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1660. Min Act: -0.0000

Data Index: 918313 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1580. Min Act: -0.0001

Data Index: 81512 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1683. Min Act: -0.0000

Data Index: 76652 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1545578 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1539. Min Act: -0.0000

Data Index: 645950 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1534. Min Act: -0.0000

Data Index: 166267 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1053936 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1427766 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1407. Min Act: -0.0001

Data Index: 414998 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1609. Min Act: -0.0000

Data Index: 730874 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1150823 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1556. Min Act: -0.0001

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1546. Min Act: -0.0001

Data Index: 1383891 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1562. Min Act: -0.0001

Data Index: 156047 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1482. Min Act: -0.0000

Data Index: 891584 (C4 (Web Text))

Max Activating Token Index: 428