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

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

Neuron 574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1445809 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0002

Data Index: 623563 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0144. Min Act: -0.0002

Data Index: 616135 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1627161 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1460468 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1517060 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1405748 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1464347 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1481252 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0002

Data Index: 423785 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0002

Data Index: 466386 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1496891 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0100. Min Act: -0.0002

Data Index: 72386 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1411346 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0099. Min Act: -0.0002

Data Index: 475090 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1526039 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1534932 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1507014 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1190348 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1392647 (Python Code)

Max Activating Token Index: 513