Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 121 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0006

Data Index: 91008 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1163584 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1146038 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0198. Min Act: -0.0006

Data Index: 168034 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0197. Min Act: -0.0006

Data Index: 716970 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0006

Data Index: 660238 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0185. Min Act: -0.0006

Data Index: 736913 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1356248 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0179. Min Act: -0.0006

Data Index: 757332 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0174. Min Act: -0.0006

Data Index: 857298 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0174. Min Act: -0.0006

Data Index: 493530 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0174. Min Act: -0.0006

Data Index: 344669 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0006

Data Index: 743797 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0182. Min Act: -0.0006

Data Index: 258723 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0181. Min Act: -0.0006

Data Index: 788360 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0176. Min Act: -0.0006

Data Index: 660275 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0178. Min Act: -0.0006

Data Index: 645045 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1195739 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0186. Min Act: -0.0006

Data Index: 517296 (C4 (Web Text))

Max Activating Token Index: 634