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

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

Neuron 3557 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: 1.4624. Min Range: -1.4624

Max Act: 1.4624. Min Act: -0.0001

Data Index: 1402230 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1481381 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1756. Min Act: -0.0001

Data Index: 1652174 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1396903 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0889. Min Act: -0.0001

Data Index: 1573352 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1024. Min Act: -0.0001

Data Index: 1511298 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0921. Min Act: -0.0000

Data Index: 1635654 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0766. Min Act: -0.0001

Data Index: 1652918 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1390505 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0562. Min Act: -0.0001

Data Index: 1429282 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1472516 (Python Code)

Max Activating Token Index: 790

Text #11

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0121. Min Act: -0.0001

Data Index: 1441925 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1653532 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9957. Min Act: -0.0001

Data Index: 1646935 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1431674 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1530018 (Python Code)

Max Activating Token Index: 310

Text #16

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9756. Min Act: -0.0001

Data Index: 1627781 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1434318 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1531640 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 1.4624. Min Range: -1.4624

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1385989 (Python Code)

Max Activating Token Index: 45