Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1809 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0003

Data Index: 401249 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0003

Data Index: 473215 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1340964 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0405. Min Act: -0.0003

Data Index: 587314 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0401. Min Act: -0.0003

Data Index: 874602 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0396. Min Act: -0.0003

Data Index: 182560 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0396. Min Act: -0.0003

Data Index: 469647 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0382. Min Act: -0.0002

Data Index: 370574 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0386. Min Act: -0.0003

Data Index: 112639 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0381. Min Act: -0.0003

Data Index: 819678 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0388. Min Act: -0.0004

Data Index: 314045 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0380. Min Act: -0.0003

Data Index: 594364 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0385. Min Act: -0.0003

Data Index: 743856 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0385. Min Act: -0.0003

Data Index: 531874 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0378. Min Act: -0.0003

Data Index: 206075 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0373. Min Act: -0.0003

Data Index: 603367 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0379. Min Act: -0.0002

Data Index: 154257 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1111222 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0368. Min Act: 0.0000

Data Index: 315668 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0368. Min Act: -0.0003

Data Index: 868430 (C4 (Web Text))

Max Activating Token Index: 94