Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3920 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1430149 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1336103 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0213. Min Act: -0.0003

Data Index: 22054 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0003

Data Index: 690078 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1027930 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0192. Min Act: -0.0003

Data Index: 888594 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1192005 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1256771 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1281512 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1037636 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0159. Min Act: -0.0003

Data Index: 661011 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0165. Min Act: -0.0003

Data Index: 853927 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1090326 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0158. Min Act: -0.0003

Data Index: 18121 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1591740 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1214672 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0157. Min Act: -0.0003

Data Index: 109012 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1083979 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1425270 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0154. Min Act: -0.0003

Data Index: 860160 (C4 (Web Text))

Max Activating Token Index: 510