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

Dataset: The Pile

Neuron 2591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0000

Data Index: 812110 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1584339 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1019896 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1034401 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1849. Min Act: 0.0001

Data Index: 1731161 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2068. Min Act: -0.0000

Data Index: 521864 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2129. Min Act: -0.0000

Data Index: 422680 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2216. Min Act: -0.0000

Data Index: 507419 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1950. Min Act: 0.0000

Data Index: 1182538 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1814. Min Act: 0.0000

Data Index: 1057562 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1328079 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1781. Min Act: 0.0000

Data Index: 169739 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1869. Min Act: -0.0000

Data Index: 276577 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1127376 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1469010 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1809. Min Act: -0.0000

Data Index: 386140 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1663726 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1915056 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1837. Min Act: 0.0000

Data Index: 1265770 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1679. Min Act: -0.0000

Data Index: 389712 (The Pile)

Max Activating Token Index: 831