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

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

Neuron 565 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: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0004

Data Index: 1052009 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0410. Min Act: -0.0004

Data Index: 1175434 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0398. Min Act: -0.0004

Data Index: 265533 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0356. Min Act: -0.0004

Data Index: 264702 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0412. Min Act: -0.0004

Data Index: 817037 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0426. Min Act: -0.0004

Data Index: 730432 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0398. Min Act: -0.0004

Data Index: 728078 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0362. Min Act: -0.0004

Data Index: 311534 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0374. Min Act: -0.0004

Data Index: 1140441 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0434. Min Act: -0.0004

Data Index: 1153351 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0400. Min Act: -0.0004

Data Index: 1091682 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1359617 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0382. Min Act: -0.0004

Data Index: 1077765 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0349. Min Act: -0.0004

Data Index: 554284 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0391. Min Act: -0.0004

Data Index: 694967 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0360. Min Act: -0.0004

Data Index: 883976 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1139239 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1061436 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0355. Min Act: -0.0004

Data Index: 451614 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1002292 (C4 (Web Text))

Max Activating Token Index: 540