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

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

Neuron 3212 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: 1.7527. Min Range: -1.7527

Max Act: 1.7284. Min Act: -0.0000

Data Index: 320661 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.7184. Min Act: -0.0000

Data Index: 249619 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.7527. Min Act: -0.0000

Data Index: 487174 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.6618. Min Act: -0.0000

Data Index: 264225 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.5625. Min Act: -0.0000

Data Index: 61514 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.5197. Min Act: -0.0000

Data Index: 956480 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.5953. Min Act: -0.0000

Data Index: 93661 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4602. Min Act: -0.0000

Data Index: 369821 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4327. Min Act: -0.0000

Data Index: 708940 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4181. Min Act: -0.0000

Data Index: 177902 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1299542 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4076. Min Act: -0.0000

Data Index: 891292 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4135. Min Act: -0.0000

Data Index: 164403 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3933. Min Act: -0.0000

Data Index: 152046 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1266640 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3905. Min Act: -0.0000

Data Index: 892702 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1042310 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3625. Min Act: -0.0000

Data Index: 386308 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2458. Min Act: -0.0000

Data Index: 259365 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2707. Min Act: -0.0000

Data Index: 295509 (C4 (Web Text))

Max Activating Token Index: 575