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

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

Neuron 1867 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: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0003

Data Index: 154484 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0194. Min Act: -0.0002

Data Index: 152945 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 625340 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0003

Data Index: 171105 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0185. Min Act: -0.0003

Data Index: 777884 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0186. Min Act: -0.0003

Data Index: 208229 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1283848 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1067243 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0174. Min Act: -0.0003

Data Index: 280061 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0179. Min Act: -0.0003

Data Index: 824523 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1236173 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0169. Min Act: -0.0003

Data Index: 615448 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0170. Min Act: -0.0003

Data Index: 168867 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0170. Min Act: -0.0003

Data Index: 926097 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1055406 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0163. Min Act: -0.0003

Data Index: 673329 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0166. Min Act: -0.0002

Data Index: 616999 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0163. Min Act: -0.0003

Data Index: 316688 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0152. Min Act: -0.0003

Data Index: 726861 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0164. Min Act: -0.0003

Data Index: 407469 (C4 (Web Text))

Max Activating Token Index: 459