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

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

Neuron 5868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0056. Min Range: -1.0056

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1601257 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9524. Min Act: -0.0000

Data Index: 605587 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8554. Min Act: -0.0000

Data Index: 608043 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8963. Min Act: -0.0000

Data Index: 740076 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1042311 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8021. Min Act: -0.0000

Data Index: 593494 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7724. Min Act: -0.0000

Data Index: 345983 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1545223 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8117. Min Act: -0.0000

Data Index: 834509 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1482340 (Python Code)

Max Activating Token Index: 482

Text #10

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7413. Min Act: -0.0000

Data Index: 593688 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1468068 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7209. Min Act: -0.0000

Data Index: 828508 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6909. Min Act: -0.0000

Data Index: 108492 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7170. Min Act: -0.0000

Data Index: 632663 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1604895 (Python Code)

Max Activating Token Index: 859

Text #16

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1033962 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6682. Min Act: -0.0000

Data Index: 7916 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1164053 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7342. Min Act: -0.0000

Data Index: 660406 (C4 (Web Text))

Max Activating Token Index: 413