Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 582 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0006

Data Index: 91918 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0170. Min Act: -0.0006

Data Index: 426112 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0153. Min Act: -0.0006

Data Index: 36159 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0145. Min Act: -0.0006

Data Index: 457821 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0147. Min Act: -0.0006

Data Index: 638511 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0145. Min Act: -0.0006

Data Index: 556243 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0144. Min Act: -0.0006

Data Index: 558395 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1148353 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0140. Min Act: -0.0006

Data Index: 476989 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0138. Min Act: -0.0006

Data Index: 354501 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0136. Min Act: -0.0006

Data Index: 379448 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0136. Min Act: -0.0006

Data Index: 131498 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0136. Min Act: -0.0006

Data Index: 612097 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0136. Min Act: -0.0006

Data Index: 731069 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0137. Min Act: -0.0006

Data Index: 219554 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0133. Min Act: -0.0006

Data Index: 11953 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0006

Data Index: 529625 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1062936 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0132. Min Act: -0.0006

Data Index: 8010 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0006

Data Index: 363007 (C4 (Web Text))

Max Activating Token Index: 58