Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1849 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1982. Min Act: -0.0002

Data Index: 1519646 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1958. Min Act: -0.0002

Data Index: 1486122 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1459698 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1848. Min Act: -0.0002

Data Index: 1477741 (Python Code)

Max Activating Token Index: 418

Text #4

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1739. Min Act: -0.0002

Data Index: 1426547 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1660. Min Act: -0.0002

Data Index: 1615443 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1786. Min Act: -0.0002

Data Index: 1370468 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1546035 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1861. Min Act: -0.0002

Data Index: 1422218 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1579. Min Act: -0.0002

Data Index: 1581733 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1690. Min Act: -0.0002

Data Index: 1504252 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1723. Min Act: -0.0002

Data Index: 1591084 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1518861 (Python Code)

Max Activating Token Index: 549

Text #13

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1576. Min Act: -0.0002

Data Index: 1415864 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1425636 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1560735 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1695. Min Act: -0.0002

Data Index: 1634103 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1679. Min Act: -0.0002

Data Index: 1422757 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1563201 (Python Code)

Max Activating Token Index: 454

Text #19

Max Range: 0.1982. Min Range: -0.1982

Max Act: 0.1403. Min Act: -0.0002

Data Index: 1592056 (Python Code)

Max Activating Token Index: 694