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

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

Neuron 2030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0422. Min Act: -0.0005

Data Index: 634250 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0005

Data Index: 411397 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0399. Min Act: -0.0005

Data Index: 1061407 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0424. Min Act: -0.0005

Data Index: 758218 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0404. Min Act: -0.0005

Data Index: 768805 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1101208 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0411. Min Act: -0.0005

Data Index: 541646 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0400. Min Act: -0.0005

Data Index: 271390 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0397. Min Act: -0.0005

Data Index: 1085013 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0386. Min Act: -0.0005

Data Index: 370044 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1097374 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1118601 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0381. Min Act: -0.0005

Data Index: 259950 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0005

Data Index: 298622 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0391. Min Act: -0.0005

Data Index: 738825 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0379. Min Act: -0.0005

Data Index: 33905 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0393. Min Act: -0.0005

Data Index: 244150 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1059121 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0383. Min Act: -0.0005

Data Index: 666236 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0374. Min Act: -0.0005

Data Index: 451626 (C4 (Web Text))

Max Activating Token Index: 250