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

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

Neuron 92 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0002

Data Index: 393841 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0832. Min Act: -0.0002

Data Index: 609587 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0804. Min Act: -0.0002

Data Index: 295402 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0792. Min Act: -0.0002

Data Index: 561269 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0728. Min Act: -0.0002

Data Index: 252848 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1320700 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0680. Min Act: -0.0002

Data Index: 685916 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0672. Min Act: -0.0002

Data Index: 464149 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0671. Min Act: -0.0002

Data Index: 623878 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1288166 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0641. Min Act: -0.0002

Data Index: 215229 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0613. Min Act: -0.0002

Data Index: 168692 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0633. Min Act: -0.0002

Data Index: 230918 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0624. Min Act: -0.0002

Data Index: 354718 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0618. Min Act: -0.0002

Data Index: 491934 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0615. Min Act: -0.0002

Data Index: 713519 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0614. Min Act: -0.0002

Data Index: 388639 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0608. Min Act: -0.0002

Data Index: 429946 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0607. Min Act: -0.0002

Data Index: 663497 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1065183 (C4 (Web Text))

Max Activating Token Index: 605