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

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

Neuron 2495 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1361564 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1634495 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2282. Min Act: -0.0001

Data Index: 260855 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2133. Min Act: -0.0001

Data Index: 614982 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2128. Min Act: -0.0001

Data Index: 144728 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1532587 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1927. Min Act: -0.0001

Data Index: 854992 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1475289 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1637995 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1138471 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1515876 (Python Code)

Max Activating Token Index: 887

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1706. Min Act: -0.0001

Data Index: 613997 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1361473 (Python Code)

Max Activating Token Index: 859

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1079731 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1030639 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1575026 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1243296 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1491875 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1115636 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1557782 (Python Code)

Max Activating Token Index: 394