Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1084824 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0345. Min Act: -0.0004

Data Index: 3863 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0354. Min Act: -0.0003

Data Index: 725764 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1335041 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1099649 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0292. Min Act: -0.0003

Data Index: 995248 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0304. Min Act: -0.0003

Data Index: 373499 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0298. Min Act: -0.0003

Data Index: 236146 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0295. Min Act: -0.0003

Data Index: 912499 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0289. Min Act: -0.0003

Data Index: 201005 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0289. Min Act: -0.0003

Data Index: 450619 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0306. Min Act: -0.0003

Data Index: 979382 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1013753 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0285. Min Act: -0.0003

Data Index: 767203 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0291. Min Act: -0.0003

Data Index: 796988 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0288. Min Act: -0.0003

Data Index: 587258 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0289. Min Act: -0.0003

Data Index: 98632 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0285. Min Act: -0.0003

Data Index: 724505 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0291. Min Act: -0.0003

Data Index: 36048 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1281840 (C4 (Web Text))

Max Activating Token Index: 196