Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 780 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0002

Data Index: 371472 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1055786 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0382. Min Act: -0.0002

Data Index: 557891 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0379. Min Act: -0.0002

Data Index: 123288 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0370. Min Act: -0.0002

Data Index: 670995 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0369. Min Act: -0.0002

Data Index: 333354 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1167658 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1109233 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0368. Min Act: -0.0002

Data Index: 908019 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1359464 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0365. Min Act: -0.0002

Data Index: 498369 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0364. Min Act: -0.0002

Data Index: 932085 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0364. Min Act: -0.0002

Data Index: 885161 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0361. Min Act: -0.0002

Data Index: 577637 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1146649 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1261641 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0358. Min Act: -0.0002

Data Index: 444592 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0358. Min Act: -0.0002

Data Index: 403907 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0357. Min Act: -0.0002

Data Index: 716772 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0348. Min Act: -0.0002

Data Index: 202432 (C4 (Web Text))

Max Activating Token Index: 995