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

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

Neuron 1816 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0000

Data Index: 505242 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1310062 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0922. Min Act: -0.0000

Data Index: 449036 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1051792 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1034761 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0867. Min Act: -0.0000

Data Index: 277550 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0822. Min Act: -0.0000

Data Index: 389256 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1153407 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0753. Min Act: -0.0000

Data Index: 944850 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0760. Min Act: -0.0000

Data Index: 381895 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0748. Min Act: -0.0000

Data Index: 854588 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1515728 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1583847 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1237158 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1237352 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1431030 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0686. Min Act: -0.0000

Data Index: 925912 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0680. Min Act: -0.0000

Data Index: 32691 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1544395 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1630148 (Python Code)

Max Activating Token Index: 943