Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4555 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9882. Min Act: -0.0003

Data Index: 1369086 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9755. Min Act: -0.0002

Data Index: 1618614 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9618. Min Act: -0.0003

Data Index: 1399594 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9545. Min Act: -0.0002

Data Index: 1537251 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9058. Min Act: -0.0002

Data Index: 1411688 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8013. Min Act: -0.0003

Data Index: 1443631 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8114. Min Act: -0.0003

Data Index: 1588824 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8134. Min Act: -0.0002

Data Index: 1526223 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8029. Min Act: -0.0003

Data Index: 1625356 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7839. Min Act: -0.0003

Data Index: 1514348 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7756. Min Act: -0.0003

Data Index: 1652010 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7483. Min Act: -0.0003

Data Index: 1559621 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7457. Min Act: -0.0002

Data Index: 1441725 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7159. Min Act: -0.0003

Data Index: 1568424 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7158. Min Act: -0.0003

Data Index: 1417554 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7198. Min Act: -0.0003

Data Index: 1534971 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6862. Min Act: -0.0002

Data Index: 1531889 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7045. Min Act: -0.0003

Data Index: 1527260 (Python Code)

Max Activating Token Index: 323

Text #18

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6931. Min Act: -0.0003

Data Index: 1641475 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6663. Min Act: -0.0003

Data Index: 1392867 (Python Code)

Max Activating Token Index: 426