Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0326. Min Act: -0.0005

Data Index: 1143536 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0005

Data Index: 689999 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1415508 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0005

Data Index: 754662 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0284. Min Act: -0.0005

Data Index: 612864 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0301. Min Act: -0.0005

Data Index: 596194 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0293. Min Act: -0.0005

Data Index: 582845 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0282. Min Act: -0.0005

Data Index: 353585 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0299. Min Act: -0.0005

Data Index: 103689 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0291. Min Act: -0.0005

Data Index: 860842 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0281. Min Act: -0.0005

Data Index: 181068 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0285. Min Act: -0.0005

Data Index: 815530 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1046435 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0270. Min Act: -0.0005

Data Index: 739070 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0295. Min Act: -0.0005

Data Index: 967093 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0276. Min Act: -0.0005

Data Index: 607074 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1089858 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0278. Min Act: -0.0005

Data Index: 271611 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0283. Min Act: -0.0005

Data Index: 353259 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0276. Min Act: -0.0005

Data Index: 513909 (C4 (Web Text))

Max Activating Token Index: 943