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

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

Neuron 1853 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0001

Data Index: 898170 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0778. Min Act: -0.0001

Data Index: 305637 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0746. Min Act: -0.0001

Data Index: 398010 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0723. Min Act: -0.0001

Data Index: 303379 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1108369 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0673. Min Act: -0.0001

Data Index: 266885 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0668. Min Act: -0.0001

Data Index: 815153 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1037902 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0635. Min Act: -0.0001

Data Index: 935403 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0654. Min Act: -0.0001

Data Index: 685430 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0626. Min Act: -0.0001

Data Index: 397357 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1274133 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0639. Min Act: -0.0001

Data Index: 52486 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1229532 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0649. Min Act: -0.0001

Data Index: 626274 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1181241 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1183172 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0585. Min Act: -0.0001

Data Index: 34360 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0580. Min Act: -0.0001

Data Index: 416609 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1019734 (C4 (Web Text))

Max Activating Token Index: 874