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

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

Neuron 4390 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0000

Data Index: 210426 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1503964 (Python Code)

Max Activating Token Index: 970

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0868. Min Act: -0.0001

Data Index: 886770 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1574633 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0858. Min Act: -0.0001

Data Index: 346743 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1465144 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1508503 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1491039 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1645237 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1490520 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1572298 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1518970 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1638251 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1374814 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1516341 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1541863 (Python Code)

Max Activating Token Index: 1022

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1521428 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0730. Min Act: -0.0001

Data Index: 477911 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1488145 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1521857 (Python Code)

Max Activating Token Index: 284