Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 856 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0213. Min Act: -0.0005

Data Index: 426955 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0005

Data Index: 393105 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0197. Min Act: -0.0005

Data Index: 38786 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0189. Min Act: -0.0005

Data Index: 646175 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0180. Min Act: -0.0005

Data Index: 881551 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0188. Min Act: -0.0005

Data Index: 553331 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0184. Min Act: -0.0005

Data Index: 954140 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0181. Min Act: -0.0005

Data Index: 781075 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0178. Min Act: -0.0005

Data Index: 678802 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0165. Min Act: -0.0005

Data Index: 602473 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0176. Min Act: -0.0005

Data Index: 809628 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0179. Min Act: -0.0005

Data Index: 636986 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0175. Min Act: -0.0005

Data Index: 22108 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1089466 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0169. Min Act: -0.0005

Data Index: 558232 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0174. Min Act: -0.0005

Data Index: 575236 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0160. Min Act: -0.0005

Data Index: 26925 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 771677 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0178. Min Act: -0.0005

Data Index: 551559 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1454341 (Python Code)

Max Activating Token Index: 488