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

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

Neuron 2557 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: 0.0170. Min Range: -0.0170

Max Act: 0.0167. Min Act: -0.0003

Data Index: 389694 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0166. Min Act: -0.0003

Data Index: 177227 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 648313 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0003

Data Index: 589520 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0003

Data Index: 840859 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0158. Min Act: -0.0003

Data Index: 336262 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0003

Data Index: 541473 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0003

Data Index: 131957 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1100257 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0003

Data Index: 474060 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0003

Data Index: 14639 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0003

Data Index: 107997 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0003

Data Index: 519924 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0003

Data Index: 826520 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0003

Data Index: 254492 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1090338 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1003957 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 735048 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1027308 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1180242 (C4 (Web Text))

Max Activating Token Index: 822