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

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

Neuron 3440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0002

Data Index: 492406 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0002

Data Index: 188443 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0002

Data Index: 751050 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0002

Data Index: 595643 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0120. Min Act: -0.0002

Data Index: 877736 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0122. Min Act: -0.0002

Data Index: 35741 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1645537 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0002

Data Index: 94714 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 305132 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0002

Data Index: 623369 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1216863 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1278173 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 967332 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 189704 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 587759 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1331960 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1219048 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0002

Data Index: 539316 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1134400 (C4 (Web Text))

Max Activating Token Index: 656