Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0002

Data Index: 736979 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0002

Data Index: 62633 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1521178 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 972608 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0133. Min Act: -0.0002

Data Index: 819815 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0002

Data Index: 42619 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0105. Min Act: -0.0002

Data Index: 997089 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0133. Min Act: -0.0002

Data Index: 601011 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0108. Min Act: -0.0002

Data Index: 754014 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0108. Min Act: -0.0002

Data Index: 56292 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1607749 (Python Code)

Max Activating Token Index: 684

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1412658 (Python Code)

Max Activating Token Index: 470

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1517804 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0002

Data Index: 960241 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0002

Data Index: 513505 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0096. Min Act: -0.0002

Data Index: 473964 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1161694 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0002

Data Index: 706311 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0095. Min Act: -0.0002

Data Index: 191210 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1269736 (C4 (Web Text))

Max Activating Token Index: 408