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

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

Neuron 3579 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: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0002

Data Index: 668140 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0130. Min Act: -0.0002

Data Index: 267055 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0127. Min Act: -0.0002

Data Index: 835791 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 310908 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1139451 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 78452 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 501195 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1441467 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 324879 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1355255 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0002

Data Index: 569237 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0120. Min Act: -0.0002

Data Index: 449158 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0120. Min Act: -0.0002

Data Index: 971629 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0117. Min Act: -0.0002

Data Index: 365361 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1039729 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0120. Min Act: -0.0002

Data Index: 969144 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0002

Data Index: 711853 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0002

Data Index: 589664 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1571681 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0002

Data Index: 160901 (C4 (Web Text))

Max Activating Token Index: 235