Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0001

Data Index: 139487 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0312. Min Act: -0.0001

Data Index: 110978 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0278. Min Act: -0.0001

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0273. Min Act: -0.0001

Data Index: 666672 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1034698 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0270. Min Act: -0.0001

Data Index: 52688 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0275. Min Act: -0.0001

Data Index: 3080 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0250. Min Act: -0.0001

Data Index: 906047 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0266. Min Act: -0.0001

Data Index: 378890 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0254. Min Act: -0.0001

Data Index: 461908 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0242. Min Act: -0.0001

Data Index: 796380 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0244. Min Act: -0.0001

Data Index: 570525 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0251. Min Act: -0.0001

Data Index: 298711 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0237. Min Act: -0.0001

Data Index: 317283 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0231. Min Act: -0.0001

Data Index: 391846 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0234. Min Act: -0.0001

Data Index: 878972 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0233. Min Act: -0.0001

Data Index: 723865 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0235. Min Act: -0.0001

Data Index: 390819 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0238. Min Act: -0.0001

Data Index: 127799 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0233. Min Act: -0.0001

Data Index: 935912 (C4 (Web Text))

Max Activating Token Index: 1002