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

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

Neuron 2296 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: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0002

Data Index: 140148 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0420. Min Act: -0.0002

Data Index: 642042 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0414. Min Act: -0.0002

Data Index: 823279 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0405. Min Act: -0.0002

Data Index: 423726 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0403. Min Act: -0.0002

Data Index: 349123 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0398. Min Act: -0.0002

Data Index: 958090 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0379. Min Act: -0.0002

Data Index: 916042 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1278819 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0378. Min Act: -0.0002

Data Index: 100308 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0378. Min Act: -0.0002

Data Index: 862649 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1320145 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0373. Min Act: -0.0002

Data Index: 913409 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0361. Min Act: -0.0002

Data Index: 237592 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0376. Min Act: -0.0002

Data Index: 503347 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1035518 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0366. Min Act: -0.0002

Data Index: 329449 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1033219 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0366. Min Act: -0.0002

Data Index: 177813 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0357. Min Act: -0.0002

Data Index: 557099 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0361. Min Act: -0.0002

Data Index: 598154 (C4 (Web Text))

Max Activating Token Index: 734