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

Dataset: The Pile

Neuron 2667 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.4520. Min Act: -0.0000

Data Index: 160477 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.3188. Min Act: -0.0000

Data Index: 747715 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1959. Min Act: -0.0000

Data Index: 830413 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2537. Min Act: -0.0000

Data Index: 14447 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1690. Min Act: -0.0000

Data Index: 870166 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.2332. Min Act: -0.0000

Data Index: 389374 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1674. Min Act: -0.0000

Data Index: 753426 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1134404 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1050887 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1305. Min Act: -0.0000

Data Index: 766011 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1079. Min Act: -0.0000

Data Index: 368900 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0425. Min Act: -0.0000

Data Index: 216458 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1032. Min Act: -0.0001

Data Index: 979110 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1055812 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1327716 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0609. Min Act: -0.0000

Data Index: 836069 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1059303 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0940. Min Act: -0.0000

Data Index: 971735 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1270468 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 1.4520. Min Range: -1.4520

Max Act: 1.0169. Min Act: -0.0000

Data Index: 622660 (The Pile)

Max Activating Token Index: 804