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

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

Neuron 1750 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: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0003

Data Index: 935770 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0133. Min Act: -0.0002

Data Index: 677480 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0002

Data Index: 311988 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0124. Min Act: -0.0002

Data Index: 216184 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0002

Data Index: 910403 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0128. Min Act: -0.0002

Data Index: 151675 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0125. Min Act: -0.0002

Data Index: 126425 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0120. Min Act: -0.0002

Data Index: 937189 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1278711 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0097. Min Act: -0.0002

Data Index: 539566 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0122. Min Act: -0.0002

Data Index: 919739 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1054822 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0122. Min Act: -0.0002

Data Index: 515990 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1141818 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0128. Min Act: -0.0002

Data Index: 619445 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0110. Min Act: -0.0002

Data Index: 585913 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0131. Min Act: -0.0002

Data Index: 709869 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0120. Min Act: -0.0002

Data Index: 992937 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0102. Min Act: -0.0002

Data Index: 559852 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0113. Min Act: -0.0002

Data Index: 6478 (C4 (Web Text))

Max Activating Token Index: 405