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

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

Neuron 2493 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: 1.3534. Min Range: -1.3534

Max Act: 1.3534. Min Act: -0.0000

Data Index: 1590993 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1494008 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1140003 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0955. Min Act: -0.0000

Data Index: 393325 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1371342 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8694. Min Act: -0.0000

Data Index: 89468 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0024. Min Act: -0.0000

Data Index: 897370 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0268. Min Act: -0.0000

Data Index: 992116 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 1.3534. Min Range: -1.3534

Max Act: 1.0059. Min Act: -0.0000

Data Index: 671717 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1549440 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1580397 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1365414 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1506249 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1404596 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1557906 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1466136 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1644358 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1381518 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1562671 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 1.3534. Min Range: -1.3534

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1471046 (Python Code)

Max Activating Token Index: 129