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

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

Neuron 3909 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0003

Data Index: 386340 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0182. Min Act: -0.0002

Data Index: 317976 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1066978 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0141. Min Act: -0.0002

Data Index: 624105 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1048520 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1144394 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0003

Data Index: 79348 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0003

Data Index: 432089 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0002

Data Index: 641508 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1294276 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1507203 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0130. Min Act: -0.0002

Data Index: 828028 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1423835 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0132. Min Act: -0.0003

Data Index: 431791 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1485356 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0127. Min Act: -0.0003

Data Index: 51917 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1650557 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0125. Min Act: -0.0002

Data Index: 352257 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0123. Min Act: -0.0003

Data Index: 650496 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0121. Min Act: -0.0003

Data Index: 578770 (C4 (Web Text))

Max Activating Token Index: 517