Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1539071 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0967. Min Act: -0.0003

Data Index: 1653497 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1428277 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1607859 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1533169 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1630607 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1608816 (Python Code)

Max Activating Token Index: 291

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1548902 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1443863 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1417109 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0632. Min Act: -0.0004

Data Index: 1640981 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1581284 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1519590 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1654344 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0638. Min Act: -0.0004

Data Index: 1461551 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1541605 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1426481 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1596199 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1492763 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1535557 (Python Code)

Max Activating Token Index: 399