Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 347 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0004

Data Index: 619434 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0184. Min Act: -0.0003

Data Index: 271797 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1321759 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1086277 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0154. Min Act: -0.0003

Data Index: 285332 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0156. Min Act: -0.0003

Data Index: 552918 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0152. Min Act: -0.0003

Data Index: 80965 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0155. Min Act: -0.0003

Data Index: 304905 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1358865 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1280959 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1232834 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0148. Min Act: -0.0004

Data Index: 482877 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0141. Min Act: -0.0003

Data Index: 898268 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0144. Min Act: -0.0004

Data Index: 135262 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1028283 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0140. Min Act: -0.0004

Data Index: 396499 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0142. Min Act: -0.0003

Data Index: 638039 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0141. Min Act: -0.0003

Data Index: 474849 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0140. Min Act: -0.0003

Data Index: 152847 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0139. Min Act: -0.0003

Data Index: 543124 (C4 (Web Text))

Max Activating Token Index: 938