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

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

Neuron 1745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0002

Data Index: 671012 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0524. Min Act: -0.0002

Data Index: 48179 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0474. Min Act: -0.0002

Data Index: 155197 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1138720 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0447. Min Act: -0.0002

Data Index: 398031 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0445. Min Act: -0.0002

Data Index: 710221 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0436. Min Act: -0.0002

Data Index: 922044 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0442. Min Act: -0.0002

Data Index: 396795 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0443. Min Act: -0.0002

Data Index: 315728 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0413. Min Act: -0.0002

Data Index: 39300 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1288936 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0443. Min Act: -0.0002

Data Index: 806736 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1337672 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1277192 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0426. Min Act: -0.0002

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1230970 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1340995 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0419. Min Act: -0.0002

Data Index: 463729 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0431. Min Act: -0.0002

Data Index: 561095 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0415. Min Act: -0.0001

Data Index: 26729 (C4 (Web Text))

Max Activating Token Index: 380