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

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

Neuron 4686 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: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0002

Data Index: 836549 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1235687 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0138. Min Act: -0.0002

Data Index: 925189 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1219930 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0127. Min Act: -0.0002

Data Index: 988180 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0126. Min Act: -0.0002

Data Index: 86039 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0126. Min Act: -0.0002

Data Index: 67679 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1190180 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0124. Min Act: -0.0002

Data Index: 410896 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0122. Min Act: -0.0002

Data Index: 470213 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0121. Min Act: -0.0002

Data Index: 408275 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0120. Min Act: -0.0002

Data Index: 76730 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1243063 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0119. Min Act: -0.0002

Data Index: 208581 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1132452 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0113. Min Act: -0.0002

Data Index: 691245 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1272835 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0110. Min Act: -0.0002

Data Index: 834826 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1302069 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0113. Min Act: -0.0002

Data Index: 691727 (C4 (Web Text))

Max Activating Token Index: 14