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

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

Neuron 788 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: 0.1872. Min Range: -0.1872

Max Act: 0.1872. Min Act: -0.0002

Data Index: 1555304 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1669. Min Act: -0.0002

Data Index: 1451892 (Python Code)

Max Activating Token Index: 935

Text #2

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1735. Min Act: -0.0002

Data Index: 1397998 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1419736 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1480134 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1687. Min Act: -0.0002

Data Index: 1433490 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1713. Min Act: -0.0002

Data Index: 1548614 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1365743 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1464673 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1581103 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1629. Min Act: -0.0002

Data Index: 1474866 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1384205 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1512129 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1676. Min Act: -0.0002

Data Index: 1613540 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1585. Min Act: -0.0002

Data Index: 1584063 (Python Code)

Max Activating Token Index: 891

Text #15

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1629. Min Act: -0.0002

Data Index: 1373152 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1479498 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1646. Min Act: -0.0002

Data Index: 1469116 (Python Code)

Max Activating Token Index: 406

Text #18

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1638. Min Act: -0.0002

Data Index: 1438274 (Python Code)

Max Activating Token Index: 787

Text #19

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1535. Min Act: -0.0002

Data Index: 1421645 (Python Code)

Max Activating Token Index: 804