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

Dataset: The Pile

Neuron 2627 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: 0.5950. Min Range: -0.5950

Max Act: 0.5950. Min Act: -0.0000

Data Index: 684927 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1421277 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1870736 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1541743 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4815. Min Act: -0.0000

Data Index: 23159 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4745. Min Act: -0.0000

Data Index: 684331 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1880416 (The Pile)

Max Activating Token Index: 724

Text #7

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4626. Min Act: -0.0000

Data Index: 21901 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1513992 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4407. Min Act: -0.0000

Data Index: 977450 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4773. Min Act: -0.0000

Data Index: 58944 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1480964 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1155757 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1504194 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1349153 (The Pile)

Max Activating Token Index: 448

Text #15

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4256. Min Act: -0.0000

Data Index: 721963 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4287. Min Act: -0.0000

Data Index: 61723 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4271. Min Act: -0.0000

Data Index: 428592 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4110. Min Act: -0.0000

Data Index: 498809 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1229783 (The Pile)

Max Activating Token Index: 700