Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0766. Min Act: -0.0001

Data Index: 795418 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0001

Data Index: 288159 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1163940 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0616. Min Act: -0.0001

Data Index: 643818 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0663. Min Act: -0.0001

Data Index: 194225 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0608. Min Act: -0.0001

Data Index: 211637 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0620. Min Act: -0.0001

Data Index: 574193 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1059936 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1185281 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0574. Min Act: -0.0001

Data Index: 679534 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0601. Min Act: -0.0001

Data Index: 660707 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1193287 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1045583 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0486. Min Act: -0.0001

Data Index: 380056 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0523. Min Act: -0.0001

Data Index: 742351 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0541. Min Act: -0.0001

Data Index: 655681 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0538. Min Act: -0.0001

Data Index: 942143 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0528. Min Act: -0.0001

Data Index: 653595 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0572. Min Act: -0.0001

Data Index: 397006 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0529. Min Act: -0.0001

Data Index: 908488 (C4 (Web Text))

Max Activating Token Index: 601