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

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

Neuron 698 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0006

Data Index: 852236 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0006

Data Index: 150354 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1169112 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0147. Min Act: -0.0006

Data Index: 948119 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0146. Min Act: -0.0006

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1323366 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1015905 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1342721 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0140. Min Act: -0.0006

Data Index: 361584 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0131. Min Act: -0.0006

Data Index: 931286 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1171327 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1184793 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1323018 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1118713 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0121. Min Act: -0.0006

Data Index: 575944 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1343146 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0123. Min Act: -0.0006

Data Index: 230792 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1338753 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0120. Min Act: -0.0006

Data Index: 597924 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0109. Min Act: -0.0006

Data Index: 138608 (C4 (Web Text))

Max Activating Token Index: 359