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

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

Neuron 47 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: 0.0417. Min Range: -0.0417

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1016461 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0005

Data Index: 861495 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0391. Min Act: -0.0005

Data Index: 660775 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1160140 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1021725 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0399. Min Act: -0.0005

Data Index: 730378 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0397. Min Act: -0.0005

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1074580 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0383. Min Act: -0.0005

Data Index: 727318 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0359. Min Act: -0.0005

Data Index: 1009650 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0376. Min Act: -0.0005

Data Index: 409772 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0368. Min Act: -0.0005

Data Index: 655441 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0384. Min Act: -0.0005

Data Index: 740670 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1341842 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0373. Min Act: -0.0005

Data Index: 542293 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0347. Min Act: -0.0005

Data Index: 536436 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1222148 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0358. Min Act: -0.0005

Data Index: 372307 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1267084 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0338. Min Act: -0.0005

Data Index: 915388 (C4 (Web Text))

Max Activating Token Index: 562