Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1775 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0006

Data Index: 850146 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0149. Min Act: -0.0006

Data Index: 657699 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0152. Min Act: -0.0006

Data Index: 845790 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0139. Min Act: -0.0006

Data Index: 196753 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0147. Min Act: -0.0006

Data Index: 640149 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0138. Min Act: -0.0006

Data Index: 708776 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1537570 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1362954 (Python Code)

Max Activating Token Index: 886

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1144512 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0127. Min Act: -0.0006

Data Index: 390365 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0127. Min Act: -0.0006

Data Index: 874209 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0126. Min Act: -0.0006

Data Index: 68900 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1077592 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1106283 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1526296 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1168455 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0125. Min Act: -0.0006

Data Index: 719733 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1354573 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0118. Min Act: -0.0006

Data Index: 577535 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0119. Min Act: -0.0006

Data Index: 976992 (C4 (Web Text))

Max Activating Token Index: 424