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

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

Neuron 3667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.6157. Min Act: -0.0001

Data Index: 928760 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5709. Min Act: -0.0001

Data Index: 1232954 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1128461 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5608. Min Act: -0.0001

Data Index: 614067 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5415. Min Act: -0.0001

Data Index: 174930 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5637. Min Act: -0.0001

Data Index: 897566 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5416. Min Act: -0.0001

Data Index: 912066 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5368. Min Act: -0.0001

Data Index: 633713 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5141. Min Act: -0.0001

Data Index: 287674 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5128. Min Act: -0.0001

Data Index: 615938 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5132. Min Act: -0.0001

Data Index: 927806 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5225. Min Act: -0.0001

Data Index: 258484 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5068. Min Act: -0.0001

Data Index: 549715 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4901. Min Act: -0.0001

Data Index: 968937 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4997. Min Act: -0.0001

Data Index: 311020 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5310. Min Act: -0.0001

Data Index: 593666 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5118. Min Act: -0.0001

Data Index: 564660 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4813. Min Act: -0.0001

Data Index: 810061 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5149. Min Act: -0.0001

Data Index: 319028 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4947. Min Act: -0.0001

Data Index: 1093663 (C4 (Web Text))

Max Activating Token Index: 28