Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1600 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0006

Data Index: 596232 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0530. Min Act: -0.0006

Data Index: 471948 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0443. Min Act: -0.0006

Data Index: 817384 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0430. Min Act: -0.0006

Data Index: 897132 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0414. Min Act: -0.0006

Data Index: 164427 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0432. Min Act: -0.0006

Data Index: 1226471 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0404. Min Act: -0.0006

Data Index: 327757 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0408. Min Act: -0.0006

Data Index: 512288 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1025754 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0386. Min Act: -0.0006

Data Index: 426596 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0390. Min Act: -0.0006

Data Index: 227847 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0395. Min Act: -0.0006

Data Index: 351722 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1169776 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0378. Min Act: -0.0006

Data Index: 629766 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0401. Min Act: -0.0006

Data Index: 675204 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0376. Min Act: -0.0006

Data Index: 914104 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1036419 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0372. Min Act: -0.0006

Data Index: 521459 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0375. Min Act: -0.0006

Data Index: 581641 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0363. Min Act: -0.0006

Data Index: 300025 (C4 (Web Text))

Max Activating Token Index: 287