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

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

Neuron 3799 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: 0.0375. Min Range: -0.0375

Max Act: 0.0372. Min Act: -0.0002

Data Index: 934095 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1300907 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1057809 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0371. Min Act: -0.0002

Data Index: 493760 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1037616 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1062880 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1572847 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1623242 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0362. Min Act: -0.0002

Data Index: 10982 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0361. Min Act: -0.0002

Data Index: 30891 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0359. Min Act: -0.0002

Data Index: 758419 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1502247 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0346. Min Act: -0.0002

Data Index: 111386 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0353. Min Act: -0.0002

Data Index: 372732 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0352. Min Act: -0.0002

Data Index: 115458 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1041889 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0344. Min Act: -0.0002

Data Index: 425220 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1271229 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0349. Min Act: -0.0002

Data Index: 258379 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0348. Min Act: -0.0002

Data Index: 157667 (C4 (Web Text))

Max Activating Token Index: 767