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

Dataset: The Pile

Neuron 2655 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: 0.8426. Min Range: -0.8426

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1440951 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6994. Min Act: -0.0000

Data Index: 617701 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1204536 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1242647 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7285. Min Act: -0.0000

Data Index: 328990 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6996. Min Act: -0.0000

Data Index: 79534 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1454833 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1597547 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1887078 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1009929 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1471416 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6338. Min Act: -0.0000

Data Index: 259746 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1435498 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1858020 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6441. Min Act: -0.0000

Data Index: 572017 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6888. Min Act: -0.0000

Data Index: 847097 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1081391 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6972. Min Act: -0.0000

Data Index: 130681 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6530. Min Act: -0.0000

Data Index: 293991 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.6231. Min Act: -0.0000

Data Index: 759831 (The Pile)

Max Activating Token Index: 218