Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2229. Min Act: -0.0000

Data Index: 269810 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2320. Min Act: -0.0000

Data Index: 927000 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1044267 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1828180 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1610096 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1492746 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1920. Min Act: -0.0000

Data Index: 438426 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1868676 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1936. Min Act: -0.0000

Data Index: 860246 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1945. Min Act: -0.0000

Data Index: 518930 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1919. Min Act: -0.0000

Data Index: 165571 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1967895 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1045040 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1821. Min Act: -0.0000

Data Index: 500069 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1749. Min Act: -0.0000

Data Index: 474670 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1783521 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1363273 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1849. Min Act: -0.0000

Data Index: 455533 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1180904 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.2320. Min Range: -0.2320

Max Act: 0.1746. Min Act: -0.0001

Data Index: 444067 (The Pile)

Max Activating Token Index: 204