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

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

Neuron 2318 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1151374 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9236. Min Act: -0.0000

Data Index: 231980 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7667. Min Act: -0.0000

Data Index: 661497 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8438. Min Act: -0.0000

Data Index: 969896 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7031. Min Act: -0.0000

Data Index: 366797 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6314. Min Act: -0.0000

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6602. Min Act: 0.0000

Data Index: 92557 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6490. Min Act: -0.0000

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5689. Min Act: -0.0000

Data Index: 292790 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6526. Min Act: -0.0000

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6105. Min Act: -0.0000

Data Index: 104323 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6404. Min Act: -0.0000

Data Index: 262940 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5842. Min Act: -0.0000

Data Index: 475826 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6242. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5813. Min Act: -0.0000

Data Index: 147341 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5955. Min Act: -0.0000

Data Index: 160787 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6627. Min Act: -0.0000

Data Index: 370986 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5888. Min Act: -0.0000

Data Index: 383089 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5658. Min Act: -0.0000

Data Index: 140102 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5397. Min Act: -0.0000

Data Index: 993867 (C4 (Web Text))

Max Activating Token Index: 558