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

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

Neuron 334 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: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0005

Data Index: 949610 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0414. Min Act: -0.0005

Data Index: 819416 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0386. Min Act: -0.0005

Data Index: 126362 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1097356 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1127558 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0005

Data Index: 23053 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0366. Min Act: -0.0004

Data Index: 775140 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0367. Min Act: -0.0005

Data Index: 769843 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0377. Min Act: -0.0005

Data Index: 1269747 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0365. Min Act: -0.0005

Data Index: 357102 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0359. Min Act: -0.0005

Data Index: 1100254 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0360. Min Act: -0.0005

Data Index: 338684 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0358. Min Act: -0.0005

Data Index: 170707 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0342. Min Act: -0.0005

Data Index: 764037 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0333. Min Act: -0.0005

Data Index: 792537 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0351. Min Act: -0.0005

Data Index: 90425 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0356. Min Act: -0.0005

Data Index: 461989 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0348. Min Act: -0.0005

Data Index: 268760 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0341. Min Act: -0.0005

Data Index: 125596 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0356. Min Act: -0.0005

Data Index: 102113 (C4 (Web Text))

Max Activating Token Index: 916