Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 217 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0705. Min Act: -0.0003

Data Index: 243226 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0003

Data Index: 38266 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0642. Min Act: -0.0003

Data Index: 255936 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1031674 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0571. Min Act: -0.0003

Data Index: 98959 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1211595 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0594. Min Act: -0.0003

Data Index: 150758 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0616. Min Act: -0.0003

Data Index: 311877 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1126342 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0624. Min Act: -0.0003

Data Index: 672186 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0595. Min Act: -0.0003

Data Index: 598034 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0513. Min Act: -0.0003

Data Index: 586149 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0645. Min Act: -0.0004

Data Index: 682962 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0564. Min Act: -0.0003

Data Index: 545351 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0620. Min Act: -0.0003

Data Index: 176475 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0563. Min Act: -0.0003

Data Index: 604023 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0520. Min Act: -0.0003

Data Index: 410073 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0635. Min Act: -0.0003

Data Index: 79707 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0585. Min Act: -0.0003

Data Index: 768181 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0581. Min Act: -0.0003

Data Index: 780478 (C4 (Web Text))

Max Activating Token Index: 643