Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2010 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0004

Data Index: 533088 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0133. Min Act: -0.0004

Data Index: 991333 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0004

Data Index: 934585 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1264395 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0004

Data Index: 685970 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0004

Data Index: 401982 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1244926 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0004

Data Index: 1201387 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0004

Data Index: 1320987 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0110. Min Act: -0.0004

Data Index: 727570 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0004

Data Index: 137810 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0105. Min Act: -0.0004

Data Index: 21903 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0107. Min Act: -0.0004

Data Index: 644384 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0107. Min Act: -0.0004

Data Index: 27827 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1274180 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0107. Min Act: -0.0004

Data Index: 758186 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1101133 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0105. Min Act: -0.0004

Data Index: 838973 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0102. Min Act: -0.0004

Data Index: 1184510 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0097. Min Act: -0.0004

Data Index: 263294 (C4 (Web Text))

Max Activating Token Index: 435