Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 820 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0002

Data Index: 940497 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1335374 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0469. Min Act: -0.0002

Data Index: 143444 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0490. Min Act: -0.0002

Data Index: 327293 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1010596 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1294051 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1262865 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0417. Min Act: -0.0002

Data Index: 412713 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0403. Min Act: -0.0003

Data Index: 794097 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0407. Min Act: -0.0003

Data Index: 895916 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0397. Min Act: -0.0002

Data Index: 100889 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1218543 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0389. Min Act: -0.0002

Data Index: 927872 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0386. Min Act: -0.0003

Data Index: 377924 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1229216 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1094886 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0385. Min Act: -0.0003

Data Index: 410285 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0375. Min Act: -0.0003

Data Index: 40040 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0382. Min Act: -0.0002

Data Index: 305572 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0382. Min Act: -0.0002

Data Index: 466029 (C4 (Web Text))

Max Activating Token Index: 748