Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1406774 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1486752 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1459211 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1623445 (Python Code)

Max Activating Token Index: 748

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1620711 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1523545 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1590995 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1401511 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1414144 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1542115 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1650788 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1517013 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1465783 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1518721 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1468333 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1654102 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1649804 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1593909 (Python Code)

Max Activating Token Index: 298

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1498449 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1606011 (Python Code)

Max Activating Token Index: 526