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

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

Neuron 1734 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0003

Data Index: 734778 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0192. Min Act: -0.0004

Data Index: 892915 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0179. Min Act: -0.0004

Data Index: 1140411 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0178. Min Act: -0.0003

Data Index: 636750 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1176931 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1384091 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0172. Min Act: -0.0004

Data Index: 936937 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0171. Min Act: -0.0004

Data Index: 738977 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0171. Min Act: -0.0003

Data Index: 414905 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0167. Min Act: -0.0003

Data Index: 543099 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0166. Min Act: -0.0003

Data Index: 513135 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0162. Min Act: -0.0004

Data Index: 161676 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0161. Min Act: -0.0003

Data Index: 319651 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0156. Min Act: -0.0003

Data Index: 247763 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0003

Data Index: 529682 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0003

Data Index: 227460 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0003

Data Index: 76760 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1532793 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0004

Data Index: 81836 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0155. Min Act: -0.0003

Data Index: 512584 (C4 (Web Text))

Max Activating Token Index: 696