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

Dataset: The Pile

Neuron 1711 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.4742. Min Act: -0.0000

Data Index: 899352 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1163474 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8090. Min Act: -0.0000

Data Index: 835788 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8919. Min Act: -0.0000

Data Index: 567825 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1336145 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1632687 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1859143 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1791475 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1728297 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5420. Min Act: -0.0000

Data Index: 36904 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5315. Min Act: -0.0000

Data Index: 494532 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1950998 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1585765 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4952. Min Act: -0.0000

Data Index: 887663 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1434532 (The Pile)

Max Activating Token Index: 423

Text #15

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.5166. Min Act: -0.0000

Data Index: 363645 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1929376 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4716. Min Act: -0.0000

Data Index: 774477 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1450438 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.4907. Min Act: -0.0000

Data Index: 691253 (The Pile)

Max Activating Token Index: 615