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

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

Neuron 53 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0179. Min Act: -0.0003

Data Index: 512751 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0003

Data Index: 283476 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1258331 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0153. Min Act: -0.0003

Data Index: 830509 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1075147 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0003

Data Index: 441721 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0148. Min Act: -0.0003

Data Index: 851839 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0170. Min Act: -0.0003

Data Index: 967361 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0173. Min Act: -0.0003

Data Index: 272099 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0143. Min Act: -0.0004

Data Index: 482345 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1085366 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0143. Min Act: -0.0003

Data Index: 171710 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0148. Min Act: -0.0003

Data Index: 826135 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1176917 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0135. Min Act: -0.0003

Data Index: 812237 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0151. Min Act: -0.0003

Data Index: 317985 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0151. Min Act: -0.0003

Data Index: 687885 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0003

Data Index: 700922 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0003

Data Index: 800036 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0140. Min Act: -0.0003

Data Index: 806070 (C4 (Web Text))

Max Activating Token Index: 900