Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3008 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1217062 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0004

Data Index: 817443 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0236. Min Act: -0.0004

Data Index: 996426 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0250. Min Act: -0.0004

Data Index: 814880 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0004

Data Index: 914972 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0232. Min Act: -0.0004

Data Index: 511267 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0211. Min Act: -0.0004

Data Index: 986629 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0220. Min Act: -0.0004

Data Index: 96956 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0222. Min Act: -0.0004

Data Index: 796130 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0200. Min Act: -0.0004

Data Index: 924080 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0217. Min Act: -0.0004

Data Index: 912537 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0208. Min Act: -0.0004

Data Index: 407028 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0209. Min Act: -0.0004

Data Index: 834430 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0217. Min Act: -0.0004

Data Index: 573986 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1287925 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0160. Min Act: -0.0004

Data Index: 1083598 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0182. Min Act: -0.0004

Data Index: 1229216 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0189. Min Act: -0.0004

Data Index: 562711 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0201. Min Act: -0.0004

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0195. Min Act: -0.0004

Data Index: 486931 (C4 (Web Text))

Max Activating Token Index: 1017