Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 602 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1228535 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1557014 (Python Code)

Max Activating Token Index: 977

Text #2

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3306. Min Act: -0.0000

Data Index: 929666 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1529420 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3222. Min Act: -0.0001

Data Index: 377450 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3142. Min Act: -0.0000

Data Index: 951930 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3098. Min Act: -0.0000

Data Index: 536093 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1416904 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2893. Min Act: -0.0001

Data Index: 566700 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2794. Min Act: -0.0000

Data Index: 598974 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1532168 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1145093 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2845. Min Act: -0.0001

Data Index: 1047161 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2777. Min Act: -0.0001

Data Index: 1505028 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2759. Min Act: -0.0001

Data Index: 682688 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2645. Min Act: -0.0001

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1302879 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1063516 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1461347 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1610837 (Python Code)

Max Activating Token Index: 295