Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 818 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0004

Data Index: 413506 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0640. Min Act: -0.0004

Data Index: 1028795 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0631. Min Act: -0.0004

Data Index: 47617 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0578. Min Act: -0.0003

Data Index: 118233 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1217729 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0591. Min Act: -0.0003

Data Index: 521290 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1300170 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0582. Min Act: -0.0002

Data Index: 197154 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0575. Min Act: -0.0004

Data Index: 1269168 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0574. Min Act: -0.0004

Data Index: 537286 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1052051 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0562. Min Act: -0.0003

Data Index: 420464 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0561. Min Act: -0.0002

Data Index: 238301 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0556. Min Act: -0.0004

Data Index: 1054358 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0555. Min Act: -0.0003

Data Index: 73329 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0545. Min Act: -0.0004

Data Index: 1328286 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1297750 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0530. Min Act: -0.0001

Data Index: 582853 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1348542 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0536. Min Act: -0.0004

Data Index: 597216 (C4 (Web Text))

Max Activating Token Index: 33