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

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

Neuron 428 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1053026 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0451. Min Act: -0.0003

Data Index: 393592 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0532. Min Act: -0.0003

Data Index: 954867 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0477. Min Act: -0.0003

Data Index: 287730 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1290691 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0509. Min Act: -0.0003

Data Index: 96170 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0481. Min Act: -0.0003

Data Index: 568450 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0513. Min Act: -0.0003

Data Index: 245242 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0472. Min Act: -0.0003

Data Index: 905474 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0442. Min Act: -0.0003

Data Index: 375435 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0505. Min Act: -0.0003

Data Index: 472160 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0468. Min Act: -0.0003

Data Index: 936839 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1132431 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0486. Min Act: -0.0003

Data Index: 380266 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0461. Min Act: -0.0003

Data Index: 1342817 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0478. Min Act: -0.0003

Data Index: 3615 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0392. Min Act: -0.0003

Data Index: 329757 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1126650 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0455. Min Act: -0.0003

Data Index: 370863 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0442. Min Act: -0.0003

Data Index: 15714 (C4 (Web Text))

Max Activating Token Index: 725