Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3500 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.3436. Min Act: -0.0001

Data Index: 399880 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.1389. Min Act: -0.0001

Data Index: 379429 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.2274. Min Act: -0.0001

Data Index: 1279330 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9909. Min Act: -0.0001

Data Index: 336261 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0254. Min Act: -0.0001

Data Index: 868480 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0420. Min Act: -0.0001

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1264415 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0647. Min Act: -0.0001

Data Index: 400163 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0325. Min Act: -0.0001

Data Index: 15020 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9644. Min Act: -0.0001

Data Index: 842553 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9873. Min Act: -0.0001

Data Index: 1059307 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9774. Min Act: -0.0001

Data Index: 343559 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0233. Min Act: -0.0001

Data Index: 1162727 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.3436. Min Range: -1.3436

Max Act: 1.0234. Min Act: -0.0001

Data Index: 590787 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9780. Min Act: -0.0001

Data Index: 1025336 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9401. Min Act: -0.0001

Data Index: 410136 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9704. Min Act: -0.0001

Data Index: 1304468 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9409. Min Act: -0.0001

Data Index: 583836 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9992. Min Act: -0.0001

Data Index: 1223547 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.3436. Min Range: -1.3436

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1251227 (C4 (Web Text))

Max Activating Token Index: 621