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

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

Neuron 3036 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1265339 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0224. Min Act: -0.0002

Data Index: 57947 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0225. Min Act: -0.0002

Data Index: 991124 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0220. Min Act: -0.0002

Data Index: 940483 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1186494 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0215. Min Act: -0.0002

Data Index: 746321 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0214. Min Act: -0.0002

Data Index: 652869 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0212. Min Act: -0.0002

Data Index: 789103 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1226456 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0002

Data Index: 643283 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0002

Data Index: 841903 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0208. Min Act: -0.0002

Data Index: 913159 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0002

Data Index: 348943 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1027571 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0205. Min Act: -0.0002

Data Index: 48016 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0205. Min Act: -0.0002

Data Index: 30493 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0002

Data Index: 594281 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0203. Min Act: -0.0002

Data Index: 970895 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0198. Min Act: -0.0002

Data Index: 467091 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0201. Min Act: -0.0002

Data Index: 285219 (C4 (Web Text))

Max Activating Token Index: 44