Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3877 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0003

Data Index: 424715 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1345227 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1294245 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0137. Min Act: -0.0003

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0003

Data Index: 542738 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0138. Min Act: -0.0003

Data Index: 774791 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1255169 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0003

Data Index: 310698 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0003

Data Index: 829578 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0003

Data Index: 313832 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0003

Data Index: 655905 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1645312 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1186519 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1243316 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0002

Data Index: 16559 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0003

Data Index: 753406 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0003

Data Index: 104308 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0003

Data Index: 794263 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1507334 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0003

Data Index: 833288 (C4 (Web Text))

Max Activating Token Index: 256