Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0973. Min Act: -0.0001

Data Index: 94678 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0909. Min Act: -0.0001

Data Index: 912509 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0828. Min Act: -0.0001

Data Index: 560145 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0879. Min Act: -0.0001

Data Index: 125393 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0755. Min Act: -0.0001

Data Index: 823961 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0696. Min Act: -0.0001

Data Index: 289570 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0632. Min Act: -0.0001

Data Index: 895746 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0712. Min Act: -0.0001

Data Index: 837474 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1083572 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0727. Min Act: -0.0001

Data Index: 607970 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0621. Min Act: -0.0001

Data Index: 453266 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0693. Min Act: -0.0002

Data Index: 356287 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0617. Min Act: -0.0001

Data Index: 622199 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0638. Min Act: -0.0001

Data Index: 726687 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1219558 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0661. Min Act: -0.0001

Data Index: 615876 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1231276 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0626. Min Act: -0.0001

Data Index: 281022 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0628. Min Act: -0.0001

Data Index: 345958 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0973. Min Range: -0.0973

Max Act: 0.0624. Min Act: -0.0001

Data Index: 673802 (C4 (Web Text))

Max Activating Token Index: 180