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

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

Neuron 4353 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: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1338724 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0769. Min Act: -0.0001

Data Index: 77769 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0741. Min Act: -0.0001

Data Index: 413846 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0700. Min Act: -0.0001

Data Index: 480683 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1142619 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1302347 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0713. Min Act: -0.0001

Data Index: 278632 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0643. Min Act: -0.0001

Data Index: 864566 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0688. Min Act: -0.0001

Data Index: 144852 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0672. Min Act: -0.0000

Data Index: 440052 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0628. Min Act: -0.0001

Data Index: 719891 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0624. Min Act: -0.0001

Data Index: 268649 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0676. Min Act: -0.0000

Data Index: 114048 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0669. Min Act: -0.0001

Data Index: 387796 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0570. Min Act: -0.0000

Data Index: 123579 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0603. Min Act: -0.0001

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0560. Min Act: -0.0001

Data Index: 7934 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0631. Min Act: -0.0001

Data Index: 265116 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0636. Min Act: -0.0001

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0616. Min Act: -0.0000

Data Index: 165879 (C4 (Web Text))

Max Activating Token Index: 69