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

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

Neuron 4172 in Layer 0

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: -0.0002

Data Index: 67331 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1089838 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0164. Min Act: -0.0002

Data Index: 220303 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1155367 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1340310 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0166. Min Act: -0.0002

Data Index: 152135 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1165452 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0002

Data Index: 152183 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0158. Min Act: -0.0002

Data Index: 679045 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0002

Data Index: 934432 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1070958 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0002

Data Index: 539125 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 466216 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0002

Data Index: 310138 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0002

Data Index: 405707 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0002

Data Index: 782928 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0002

Data Index: 314121 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1031125 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0002

Data Index: 442508 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 624695 (C4 (Web Text))

Max Activating Token Index: 513