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

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

Neuron 3689 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.3941. Min Act: -0.0000

Data Index: 1584210 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.0377. Min Act: -0.0000

Data Index: 1503257 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.3283. Min Act: -0.0000

Data Index: 1575280 (Python Code)

Max Activating Token Index: 615

Text #3

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.0889. Min Act: 0.0000

Data Index: 1568785 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.9012. Min Act: -0.0000

Data Index: 1640012 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.1125. Min Act: -0.0000

Data Index: 1386185 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.9636. Min Act: -0.0000

Data Index: 1609930 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.9304. Min Act: -0.0000

Data Index: 1495189 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.8904. Min Act: -0.0000

Data Index: 1651404 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.8515. Min Act: -0.0000

Data Index: 1612989 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1615842 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.6649. Min Act: -0.0000

Data Index: 1534380 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.9157. Min Act: -0.0000

Data Index: 1396939 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.7527. Min Act: -0.0000

Data Index: 1641137 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.4738. Min Act: -0.0000

Data Index: 1608091 (Python Code)

Max Activating Token Index: 691

Text #15

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.7376. Min Act: -0.0000

Data Index: 1528641 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.7122. Min Act: -0.0000

Data Index: 1433633 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.8960. Min Act: -0.0000

Data Index: 1630730 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.6927. Min Act: -0.0000

Data Index: 1641098 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.6598. Min Act: -0.0000

Data Index: 1650607 (Python Code)

Max Activating Token Index: 715