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

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

Neuron 2662 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0002

Data Index: 283371 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1142070 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1057449 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0201. Min Act: -0.0002

Data Index: 994860 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1260993 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0198. Min Act: -0.0002

Data Index: 771027 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0194. Min Act: -0.0002

Data Index: 131990 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0195. Min Act: -0.0002

Data Index: 209760 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0187. Min Act: -0.0002

Data Index: 918411 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0186. Min Act: -0.0002

Data Index: 415045 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0171. Min Act: -0.0002

Data Index: 162483 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1303433 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0172. Min Act: -0.0002

Data Index: 577541 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1039770 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0165. Min Act: -0.0002

Data Index: 578744 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1224430 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0173. Min Act: -0.0002

Data Index: 539542 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0176. Min Act: -0.0002

Data Index: 752089 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0176. Min Act: -0.0002

Data Index: 308302 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0168. Min Act: -0.0002

Data Index: 916015 (C4 (Web Text))

Max Activating Token Index: 125