Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5878 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1345792 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0619. Min Act: -0.0002

Data Index: 630897 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0543. Min Act: -0.0002

Data Index: 399185 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1310844 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0523. Min Act: -0.0002

Data Index: 295686 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1032953 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1019015 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0441. Min Act: -0.0002

Data Index: 386292 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0445. Min Act: -0.0002

Data Index: 562920 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1007891 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0418. Min Act: -0.0002

Data Index: 460061 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0419. Min Act: -0.0002

Data Index: 849697 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1191414 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0417. Min Act: -0.0002

Data Index: 332579 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0411. Min Act: -0.0002

Data Index: 576919 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1163559 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0394. Min Act: -0.0002

Data Index: 331018 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0405. Min Act: -0.0002

Data Index: 642368 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1008513 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0396. Min Act: -0.0002

Data Index: 374217 (C4 (Web Text))

Max Activating Token Index: 47