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

Dataset: The Pile

Neuron 4500 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: 1.9060. Min Range: -1.9060

Max Act: 1.8536. Min Act: -0.0000

Data Index: 536117 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.9060. Min Act: -0.0000

Data Index: 448482 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7843. Min Act: -0.0000

Data Index: 335602 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6773. Min Act: -0.0000

Data Index: 866884 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1799836 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7664. Min Act: -0.0000

Data Index: 1413808 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7592. Min Act: -0.0000

Data Index: 119128 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1513838 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7329. Min Act: -0.0000

Data Index: 73783 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6041. Min Act: -0.0000

Data Index: 601679 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1016697 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1234967 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6677. Min Act: -0.0000

Data Index: 1622125 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7485. Min Act: -0.0000

Data Index: 953685 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6568. Min Act: -0.0000

Data Index: 573526 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1379332 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.7209. Min Act: -0.0000

Data Index: 1849972 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.5213. Min Act: -0.0000

Data Index: 537166 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1730853 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 1.9060. Min Range: -1.9060

Max Act: 1.5952. Min Act: -0.0000

Data Index: 1602451 (The Pile)

Max Activating Token Index: 698