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

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

Neuron 258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1185305 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.1041. Min Act: -0.0001

Data Index: 951195 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1068957 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1164633 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0930. Min Act: -0.0001

Data Index: 439793 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1557659 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0768. Min Act: -0.0001

Data Index: 19416 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1368282 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0819. Min Act: -0.0001

Data Index: 107532 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1236039 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1174353 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0792. Min Act: -0.0001

Data Index: 861820 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1340462 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1225798 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1606600 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0762. Min Act: -0.0001

Data Index: 138729 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0773. Min Act: -0.0001

Data Index: 567979 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1432321 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0733. Min Act: -0.0001

Data Index: 590058 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1041. Min Range: -0.1041

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1421342 (Python Code)

Max Activating Token Index: 465