Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0001

Data Index: 149420 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0134. Min Act: -0.0002

Data Index: 69121 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0130. Min Act: -0.0001

Data Index: 195840 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0127. Min Act: -0.0002

Data Index: 385011 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0120. Min Act: -0.0001

Data Index: 770799 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0110. Min Act: -0.0001

Data Index: 1324013 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1322960 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0115. Min Act: -0.0001

Data Index: 373585 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0120. Min Act: -0.0001

Data Index: 439421 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0103. Min Act: -0.0002

Data Index: 450915 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1273566 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0002

Data Index: 778928 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0001

Data Index: 672816 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1304356 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0104. Min Act: -0.0002

Data Index: 568967 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0001

Data Index: 1130468 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0107. Min Act: -0.0002

Data Index: 773850 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0104. Min Act: -0.0001

Data Index: 140903 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0001

Data Index: 1222815 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0102. Min Act: -0.0001

Data Index: 676273 (C4 (Web Text))

Max Activating Token Index: 642