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

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

Neuron 2618 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0002

Data Index: 664447 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0288. Min Act: -0.0002

Data Index: 788621 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0295. Min Act: -0.0002

Data Index: 939894 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0284. Min Act: -0.0002

Data Index: 476136 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1113430 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0285. Min Act: -0.0002

Data Index: 778640 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1275572 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0290. Min Act: -0.0002

Data Index: 136586 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0266. Min Act: -0.0002

Data Index: 633297 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0267. Min Act: -0.0002

Data Index: 307377 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0265. Min Act: -0.0002

Data Index: 514059 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1012552 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0260. Min Act: -0.0002

Data Index: 633954 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0262. Min Act: -0.0002

Data Index: 474945 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1304283 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0266. Min Act: -0.0002

Data Index: 622043 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0263. Min Act: -0.0002

Data Index: 769958 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0274. Min Act: -0.0002

Data Index: 875025 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0277. Min Act: -0.0002

Data Index: 530197 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0262. Min Act: -0.0002

Data Index: 382084 (C4 (Web Text))

Max Activating Token Index: 942