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

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

Neuron 1740 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: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0000

Data Index: 984160 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1136961 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1179. Min Act: -0.0000

Data Index: 178848 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1625795 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1074. Min Act: -0.0000

Data Index: 408591 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1017. Min Act: -0.0000

Data Index: 788401 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1341276 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0999. Min Act: -0.0000

Data Index: 47756 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0992. Min Act: -0.0000

Data Index: 967222 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0978. Min Act: -0.0000

Data Index: 484493 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0980. Min Act: -0.0000

Data Index: 165029 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1404584 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1556859 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1589123 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1486659 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0935. Min Act: -0.0000

Data Index: 229783 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0963. Min Act: -0.0000

Data Index: 75142 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0891. Min Act: -0.0000

Data Index: 355977 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0892. Min Act: -0.0000

Data Index: 159853 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0855. Min Act: -0.0000

Data Index: 829846 (C4 (Web Text))

Max Activating Token Index: 630