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

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

Neuron 1981 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: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0003

Data Index: 714649 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0378. Min Act: -0.0003

Data Index: 710201 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0364. Min Act: -0.0003

Data Index: 200836 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0365. Min Act: -0.0003

Data Index: 141837 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0368. Min Act: -0.0002

Data Index: 687232 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1020640 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0339. Min Act: -0.0002

Data Index: 705120 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0342. Min Act: -0.0003

Data Index: 871945 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1119916 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0339. Min Act: -0.0003

Data Index: 999579 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0335. Min Act: -0.0002

Data Index: 246322 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0321. Min Act: -0.0004

Data Index: 605170 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0317. Min Act: -0.0002

Data Index: 401325 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0311. Min Act: -0.0002

Data Index: 581382 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0313. Min Act: -0.0003

Data Index: 613536 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0311. Min Act: -0.0003

Data Index: 355957 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0315. Min Act: -0.0001

Data Index: 68434 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0308. Min Act: -0.0002

Data Index: 816092 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0306. Min Act: -0.0003

Data Index: 74352 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0306. Min Act: -0.0004

Data Index: 585854 (C4 (Web Text))

Max Activating Token Index: 90