Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1649791 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1580118 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1432445 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1508605 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1462240 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1472447 (Python Code)

Max Activating Token Index: 402

Text #6

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1436013 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1643812 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1643781 (Python Code)

Max Activating Token Index: 873

Text #9

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1654338 (Python Code)

Max Activating Token Index: 979

Text #10

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1616457 (Python Code)

Max Activating Token Index: 957

Text #11

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1388309 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1392168 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1617917 (Python Code)

Max Activating Token Index: 909

Text #14

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1471864 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1509697 (Python Code)

Max Activating Token Index: 605

Text #16

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1485550 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1568180 (Python Code)

Max Activating Token Index: 942

Text #18

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1479211 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.1713. Min Range: -0.1713

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1439647 (Python Code)

Max Activating Token Index: 368