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

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

Neuron 1612 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.6546. Min Act: -0.0000

Data Index: 1641645 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.3154. Min Act: -0.0000

Data Index: 1578433 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.4143. Min Act: -0.0000

Data Index: 1455125 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.3830. Min Act: -0.0000

Data Index: 1622619 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.5441. Min Act: -0.0000

Data Index: 1366729 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1112382 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.2765. Min Act: -0.0000

Data Index: 1591694 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.1095. Min Act: -0.0000

Data Index: 1365531 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.1917. Min Act: -0.0000

Data Index: 1395109 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.1393. Min Act: -0.0000

Data Index: 1352398 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.1269. Min Act: -0.0000

Data Index: 1496030 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0992. Min Act: -0.0000

Data Index: 1481917 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0941. Min Act: -0.0000

Data Index: 1423585 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.2108. Min Act: -0.0000

Data Index: 1425098 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.1709. Min Act: -0.0000

Data Index: 1642123 (Python Code)

Max Activating Token Index: 838

Text #15

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0558. Min Act: -0.0000

Data Index: 1433700 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0619. Min Act: -0.0000

Data Index: 1416752 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0582. Min Act: -0.0000

Data Index: 1628139 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 2.6546. Min Range: -2.6546

Max Act: 1.9215. Min Act: -0.0000

Data Index: 1642707 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 2.6546. Min Range: -2.6546

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1531362 (Python Code)

Max Activating Token Index: 714