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

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

Neuron 1290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0002

Data Index: 162196 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0708. Min Act: -0.0002

Data Index: 740368 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0728. Min Act: -0.0002

Data Index: 482289 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0732. Min Act: -0.0002

Data Index: 979362 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0680. Min Act: -0.0002

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0669. Min Act: -0.0002

Data Index: 237804 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0703. Min Act: -0.0002

Data Index: 735274 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0693. Min Act: -0.0002

Data Index: 374041 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1234721 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1263382 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0658. Min Act: -0.0002

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1171840 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0668. Min Act: -0.0002

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0636. Min Act: -0.0002

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0641. Min Act: -0.0002

Data Index: 73318 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1323169 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0659. Min Act: -0.0002

Data Index: 652228 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0655. Min Act: -0.0002

Data Index: 615013 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0634. Min Act: -0.0002

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0628. Min Act: -0.0002

Data Index: 115565 (C4 (Web Text))

Max Activating Token Index: 136