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

Dataset: The Pile

Neuron 4878 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: 1.2622. Min Range: -1.2622

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1823161 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1116734 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1929655 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1483. Min Act: -0.0000

Data Index: 319643 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0734. Min Act: -0.0000

Data Index: 245187 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1266. Min Act: -0.0000

Data Index: 470093 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1104. Min Act: -0.0000

Data Index: 910347 (The Pile)

Max Activating Token Index: 887

Text #7

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1315313 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1506506 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1031. Min Act: -0.0000

Data Index: 678893 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1281452 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1227519 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0798. Min Act: -0.0000

Data Index: 189349 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9928. Min Act: -0.0000

Data Index: 894584 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 1.2622. Min Range: -1.2622

Max Act: 1.0250. Min Act: -0.0000

Data Index: 435303 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1586160 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1134452 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1389147 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1383344 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.2622. Min Range: -1.2622

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1891001 (The Pile)

Max Activating Token Index: 40