Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1953 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.4016. Min Act: -0.0000

Data Index: 664568 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.3123. Min Act: -0.0000

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2390. Min Act: -0.0000

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1300473 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1282100 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1047411 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2213. Min Act: -0.0000

Data Index: 956880 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2260. Min Act: -0.0000

Data Index: 324347 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1090702 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2216. Min Act: -0.0000

Data Index: 617795 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2278. Min Act: -0.0000

Data Index: 592828 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2272. Min Act: -0.0000

Data Index: 474055 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1287371 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2298. Min Act: -0.0000

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2134. Min Act: -0.0000

Data Index: 85447 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2157. Min Act: -0.0000

Data Index: 114633 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.4016. Min Range: -0.4016

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1447802 (Python Code)

Max Activating Token Index: 658