Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1606 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0004

Data Index: 234423 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1374663 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1178333 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0135. Min Act: -0.0004

Data Index: 181758 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0134. Min Act: -0.0004

Data Index: 1360769 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1648181 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0131. Min Act: -0.0003

Data Index: 268711 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0004

Data Index: 207839 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1617498 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0128. Min Act: -0.0004

Data Index: 764298 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0127. Min Act: -0.0004

Data Index: 980684 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0127. Min Act: -0.0004

Data Index: 449312 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0003

Data Index: 850149 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0124. Min Act: -0.0004

Data Index: 24889 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0124. Min Act: -0.0004

Data Index: 1150227 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0122. Min Act: -0.0004

Data Index: 1392736 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0121. Min Act: -0.0003

Data Index: 727231 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1370710 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0004

Data Index: 297271 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0121. Min Act: -0.0004

Data Index: 268403 (C4 (Web Text))

Max Activating Token Index: 512