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

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

Neuron 6055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0000

Data Index: 409611 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0853. Min Act: -0.0000

Data Index: 822091 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1369817 (Python Code)

Max Activating Token Index: 991

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0770. Min Act: -0.0000

Data Index: 220989 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1518818 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0751. Min Act: -0.0000

Data Index: 293822 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0713. Min Act: -0.0000

Data Index: 565774 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1373097 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1469762 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1647113 (Python Code)

Max Activating Token Index: 782

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1121735 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1016184 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1612442 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0768. Min Act: -0.0000

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0666. Min Act: -0.0000

Data Index: 109196 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0647. Min Act: -0.0000

Data Index: 815952 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1517086 (Python Code)

Max Activating Token Index: 958

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1552855 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0666. Min Act: -0.0000

Data Index: 743665 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1459252 (Python Code)

Max Activating Token Index: 319