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

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

Neuron 302 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0589. Min Act: -0.0002

Data Index: 407185 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1034376 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1314164 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0426. Min Act: -0.0002

Data Index: 222559 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0414. Min Act: -0.0002

Data Index: 999334 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1300686 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0374. Min Act: -0.0002

Data Index: 781156 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1187848 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0380. Min Act: -0.0002

Data Index: 157979 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1322705 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0367. Min Act: -0.0002

Data Index: 30898 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0320. Min Act: -0.0002

Data Index: 814699 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0349. Min Act: -0.0002

Data Index: 386565 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0357. Min Act: -0.0002

Data Index: 530450 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1283088 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0356. Min Act: -0.0002

Data Index: 912045 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0357. Min Act: -0.0002

Data Index: 717106 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0375. Min Act: -0.0002

Data Index: 277618 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0364. Min Act: -0.0002

Data Index: 940358 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0353. Min Act: -0.0002

Data Index: 611100 (C4 (Web Text))

Max Activating Token Index: 571