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

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

Neuron 1438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 425328 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0541. Min Act: -0.0002

Data Index: 431409 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0420. Min Act: -0.0002

Data Index: 538654 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0443. Min Act: -0.0002

Data Index: 26324 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0397. Min Act: -0.0002

Data Index: 501876 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0386. Min Act: -0.0002

Data Index: 311154 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0427. Min Act: -0.0002

Data Index: 773076 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1000113 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0388. Min Act: -0.0002

Data Index: 431031 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0347. Min Act: -0.0002

Data Index: 746898 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0404. Min Act: -0.0002

Data Index: 554590 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0342. Min Act: -0.0002

Data Index: 753346 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0339. Min Act: -0.0002

Data Index: 628297 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0374. Min Act: -0.0002

Data Index: 570311 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0326. Min Act: -0.0002

Data Index: 551078 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1655623 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1042616 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0388. Min Act: -0.0002

Data Index: 937359 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1024914 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1054559 (C4 (Web Text))

Max Activating Token Index: 47