Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2001 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0405. Min Act: -0.0003

Data Index: 268233 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0003

Data Index: 935221 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1044686 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0400. Min Act: -0.0003

Data Index: 639300 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1062129 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1048336 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0396. Min Act: -0.0003

Data Index: 338500 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0390. Min Act: -0.0003

Data Index: 413000 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0385. Min Act: -0.0003

Data Index: 512847 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1349911 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0379. Min Act: -0.0003

Data Index: 270843 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0384. Min Act: -0.0003

Data Index: 665350 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0380. Min Act: -0.0003

Data Index: 434318 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0375. Min Act: -0.0003

Data Index: 253798 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0379. Min Act: -0.0003

Data Index: 686173 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0376. Min Act: -0.0003

Data Index: 421171 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0378. Min Act: -0.0003

Data Index: 126939 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0374. Min Act: -0.0003

Data Index: 341100 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0369. Min Act: -0.0003

Data Index: 489672 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0373. Min Act: -0.0003

Data Index: 450563 (C4 (Web Text))

Max Activating Token Index: 26