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

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

Neuron 2915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0003

Data Index: 29597 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0156. Min Act: -0.0003

Data Index: 530837 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0166. Min Act: -0.0003

Data Index: 347779 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0163. Min Act: -0.0003

Data Index: 941124 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0152. Min Act: -0.0003

Data Index: 355364 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0003

Data Index: 343839 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0003

Data Index: 167299 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0147. Min Act: -0.0003

Data Index: 595655 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1179362 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0153. Min Act: -0.0003

Data Index: 439475 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0133. Min Act: -0.0003

Data Index: 110015 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0150. Min Act: -0.0003

Data Index: 206695 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0146. Min Act: -0.0003

Data Index: 115578 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0143. Min Act: -0.0003

Data Index: 662596 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0144. Min Act: -0.0003

Data Index: 420934 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1314664 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0138. Min Act: -0.0003

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0003

Data Index: 58392 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0150. Min Act: -0.0003

Data Index: 270688 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0137. Min Act: -0.0003

Data Index: 331694 (C4 (Web Text))

Max Activating Token Index: 306