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

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

Neuron 4821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0626. Min Act: -0.0002

Data Index: 168287 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1154316 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0002

Data Index: 640126 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1301836 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0628. Min Act: -0.0002

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0625. Min Act: -0.0002

Data Index: 510614 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0630. Min Act: -0.0002

Data Index: 674527 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1264794 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0568. Min Act: -0.0002

Data Index: 226169 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1176265 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0583. Min Act: -0.0002

Data Index: 802460 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0582. Min Act: -0.0002

Data Index: 657334 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0546. Min Act: -0.0002

Data Index: 497981 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0589. Min Act: -0.0002

Data Index: 146565 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0539. Min Act: -0.0002

Data Index: 108868 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0557. Min Act: -0.0002

Data Index: 417250 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0434. Min Act: -0.0002

Data Index: 671443 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1064961 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0482. Min Act: -0.0002

Data Index: 999460 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0537. Min Act: -0.0002

Data Index: 478537 (C4 (Web Text))

Max Activating Token Index: 685