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

Dataset: The Pile

Neuron 2228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0658. Min Act: -0.0000

Data Index: 34213 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0687. Min Act: -0.0000

Data Index: 912461 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1301967 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0635. Min Act: -0.0000

Data Index: 53027 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0707. Min Act: -0.0000

Data Index: 468588 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0721. Min Act: 0.0000

Data Index: 859593 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0634. Min Act: -0.0000

Data Index: 782765 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1579373 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1392348 (The Pile)

Max Activating Token Index: 742

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0600. Min Act: -0.0000

Data Index: 595212 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1101102 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0623. Min Act: -0.0000

Data Index: 375393 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0550. Min Act: -0.0000

Data Index: 384464 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1860963 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1811890 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1653895 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1515557 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1179830 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0529. Min Act: -0.0000

Data Index: 198175 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0478. Min Act: -0.0000

Data Index: 951800 (The Pile)

Max Activating Token Index: 983