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

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

Neuron 48 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: 0.0979. Min Range: -0.0979

Max Act: 0.0921. Min Act: -0.0000

Data Index: 179768 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0000

Data Index: 744350 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1937 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0775. Min Act: -0.0000

Data Index: 329912 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0768. Min Act: -0.0000

Data Index: 929942 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0780. Min Act: -0.0000

Data Index: 180635 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1162055 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0742. Min Act: -0.0000

Data Index: 227293 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0709. Min Act: -0.0000

Data Index: 491072 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0699. Min Act: -0.0000

Data Index: 710595 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0702. Min Act: -0.0000

Data Index: 314908 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0699. Min Act: -0.0000

Data Index: 56842 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0694. Min Act: -0.0000

Data Index: 881508 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0684. Min Act: -0.0000

Data Index: 744635 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0611. Min Act: -0.0000

Data Index: 793667 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0674. Min Act: -0.0000

Data Index: 382334 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0688. Min Act: -0.0000

Data Index: 734480 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0687. Min Act: -0.0000

Data Index: 683917 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0666. Min Act: -0.0000

Data Index: 886398 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0594. Min Act: -0.0000

Data Index: 362354 (C4 (Web Text))

Max Activating Token Index: 740