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

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

Neuron 503 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: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0002

Data Index: 941668 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0191. Min Act: -0.0002

Data Index: 827232 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0198. Min Act: -0.0002

Data Index: 161474 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0166. Min Act: -0.0002

Data Index: 357185 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0158. Min Act: -0.0002

Data Index: 185177 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0163. Min Act: -0.0002

Data Index: 545813 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1036519 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0140. Min Act: -0.0002

Data Index: 686626 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1200998 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0133. Min Act: -0.0002

Data Index: 641755 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0132. Min Act: -0.0002

Data Index: 179900 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0131. Min Act: -0.0002

Data Index: 573737 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0128. Min Act: -0.0002

Data Index: 735484 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0119. Min Act: -0.0002

Data Index: 868628 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0122. Min Act: -0.0002

Data Index: 230794 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1032333 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0130. Min Act: -0.0002

Data Index: 610597 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1234787 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0116. Min Act: -0.0002

Data Index: 558748 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1161587 (C4 (Web Text))

Max Activating Token Index: 121