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

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

Neuron 868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0001

Data Index: 237582 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1341411 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0977. Min Act: -0.0001

Data Index: 543097 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0940. Min Act: -0.0001

Data Index: 26155 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1204113 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1248211 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0874. Min Act: -0.0001

Data Index: 939032 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0901. Min Act: -0.0001

Data Index: 734170 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0839. Min Act: -0.0001

Data Index: 680337 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1047844 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1350795 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0825. Min Act: -0.0001

Data Index: 313221 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0827. Min Act: -0.0001

Data Index: 843782 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0783. Min Act: -0.0001

Data Index: 950014 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0819. Min Act: -0.0001

Data Index: 141001 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1128233 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0832. Min Act: -0.0001

Data Index: 500552 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0815. Min Act: -0.0001

Data Index: 850263 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0792. Min Act: -0.0001

Data Index: 297509 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0809. Min Act: -0.0001

Data Index: 258601 (C4 (Web Text))

Max Activating Token Index: 513