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

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

Neuron 3446 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.9447. Min Act: -0.0000

Data Index: 517027 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.6506. Min Act: -0.0000

Data Index: 871534 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.5242. Min Act: -0.0000

Data Index: 685408 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.5038. Min Act: -0.0000

Data Index: 465317 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4755. Min Act: -0.0000

Data Index: 497433 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1079181 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1289547 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1227626 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1205484 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4447. Min Act: -0.0000

Data Index: 597326 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4384. Min Act: -0.0000

Data Index: 581022 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4403. Min Act: -0.0000

Data Index: 211373 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4295. Min Act: -0.0000

Data Index: 453283 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4419. Min Act: -0.0000

Data Index: 985181 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4423. Min Act: -0.0000

Data Index: 240494 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4081. Min Act: -0.0000

Data Index: 114994 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4020. Min Act: -0.0000

Data Index: 361816 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4296. Min Act: -0.0000

Data Index: 596825 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1235951 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.9447. Min Range: -0.9447

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1082367 (C4 (Web Text))

Max Activating Token Index: 592