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

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

Neuron 474 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: 0.0355. Min Range: -0.0355

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1037043 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0002

Data Index: 807115 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0311. Min Act: -0.0002

Data Index: 616943 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0342. Min Act: -0.0002

Data Index: 392713 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0317. Min Act: -0.0002

Data Index: 113746 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0311. Min Act: -0.0002

Data Index: 294442 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0298. Min Act: -0.0002

Data Index: 153989 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1584803 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0263. Min Act: -0.0002

Data Index: 212878 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0285. Min Act: -0.0002

Data Index: 328482 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0283. Min Act: -0.0002

Data Index: 209871 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1619419 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0276. Min Act: -0.0002

Data Index: 687676 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0293. Min Act: -0.0002

Data Index: 738524 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0270. Min Act: -0.0002

Data Index: 10289 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0265. Min Act: -0.0002

Data Index: 807643 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0274. Min Act: -0.0002

Data Index: 530055 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0279. Min Act: -0.0002

Data Index: 389918 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0274. Min Act: -0.0002

Data Index: 917218 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0265. Min Act: -0.0002

Data Index: 576734 (C4 (Web Text))

Max Activating Token Index: 51