Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1326 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0003

Data Index: 700692 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1045336 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1329526 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0568. Min Act: -0.0003

Data Index: 152306 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0568. Min Act: -0.0003

Data Index: 528000 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0539. Min Act: -0.0003

Data Index: 675447 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0624. Min Act: -0.0003

Data Index: 857777 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0562. Min Act: -0.0003

Data Index: 504828 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0619. Min Act: -0.0003

Data Index: 428076 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0567. Min Act: -0.0003

Data Index: 117069 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1051920 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0500. Min Act: -0.0003

Data Index: 505563 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0527. Min Act: -0.0003

Data Index: 506304 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0508. Min Act: -0.0003

Data Index: 421468 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1080517 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0515. Min Act: -0.0003

Data Index: 837156 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1121548 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0506. Min Act: -0.0003

Data Index: 185006 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0527. Min Act: -0.0003

Data Index: 153583 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1234861 (C4 (Web Text))

Max Activating Token Index: 197