Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 25 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0377. Min Act: -0.0004

Data Index: 642410 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0383. Min Act: -0.0004

Data Index: 287367 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0371. Min Act: -0.0004

Data Index: 46102 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1312021 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0381. Min Act: -0.0004

Data Index: 133297 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0398. Min Act: -0.0004

Data Index: 176376 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0387. Min Act: -0.0004

Data Index: 66494 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0379. Min Act: -0.0004

Data Index: 51673 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0385. Min Act: -0.0004

Data Index: 1123604 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0004

Data Index: 838980 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0382. Min Act: -0.0004

Data Index: 177894 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1218585 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0395. Min Act: -0.0004

Data Index: 429475 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0362. Min Act: -0.0004

Data Index: 996660 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0374. Min Act: -0.0004

Data Index: 96404 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0339. Min Act: -0.0004

Data Index: 140599 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0380. Min Act: -0.0004

Data Index: 547815 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0378. Min Act: -0.0004

Data Index: 565893 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0352. Min Act: -0.0004

Data Index: 607789 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0345. Min Act: -0.0004

Data Index: 737459 (C4 (Web Text))

Max Activating Token Index: 907