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

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

Neuron 2704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0003

Data Index: 634055 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0960. Min Act: -0.0003

Data Index: 179863 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0857. Min Act: -0.0003

Data Index: 821724 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1001. Min Act: -0.0003

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0510. Min Act: -0.0003

Data Index: 81649 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0696. Min Act: -0.0003

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0577. Min Act: -0.0003

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0570. Min Act: -0.0003

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0597. Min Act: -0.0003

Data Index: 171122 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0478. Min Act: -0.0003

Data Index: 97891 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1268443 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0521. Min Act: -0.0003

Data Index: 700098 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0511. Min Act: -0.0003

Data Index: 431320 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0502. Min Act: -0.0003

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0471. Min Act: -0.0003

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1036629 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0411. Min Act: -0.0003

Data Index: 993374 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0397. Min Act: -0.0003

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0376. Min Act: -0.0003

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 773