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

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

Neuron 1292 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: 0.0478. Min Range: -0.0478

Max Act: 0.0453. Min Act: -0.0005

Data Index: 525141 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0005

Data Index: 276982 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0450. Min Act: -0.0005

Data Index: 76766 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0411. Min Act: -0.0005

Data Index: 1042939 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0405. Min Act: -0.0005

Data Index: 867803 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0408. Min Act: -0.0005

Data Index: 546239 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0398. Min Act: -0.0005

Data Index: 2483 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0388. Min Act: -0.0005

Data Index: 985007 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0372. Min Act: -0.0005

Data Index: 120367 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0005

Data Index: 534605 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0005

Data Index: 1136333 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0366. Min Act: -0.0005

Data Index: 983210 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0378. Min Act: -0.0005

Data Index: 196333 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0368. Min Act: -0.0005

Data Index: 185347 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0374. Min Act: -0.0005

Data Index: 532375 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0356. Min Act: -0.0005

Data Index: 1252589 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0366. Min Act: -0.0005

Data Index: 519610 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0362. Min Act: -0.0005

Data Index: 556606 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0358. Min Act: -0.0005

Data Index: 1334488 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0357. Min Act: -0.0005

Data Index: 701863 (C4 (Web Text))

Max Activating Token Index: 970