Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4253 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 700531 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 534557 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0003

Data Index: 632052 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0169. Min Act: -0.0003

Data Index: 612583 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 847906 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0003

Data Index: 925824 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1241975 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1271862 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0003

Data Index: 680815 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0003

Data Index: 176706 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 140317 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0003

Data Index: 533531 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0003

Data Index: 505604 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0003

Data Index: 304490 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0003

Data Index: 529414 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0003

Data Index: 174627 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0003

Data Index: 84586 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0003

Data Index: 392181 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1184131 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0003

Data Index: 567550 (C4 (Web Text))

Max Activating Token Index: 20