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

Dataset: The Pile

Neuron 288 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: 0.2738. Min Range: -0.2738

Max Act: 0.2738. Min Act: -0.0000

Data Index: 421708 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1822896 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2420. Min Act: -0.0000

Data Index: 962470 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2401. Min Act: -0.0000

Data Index: 360280 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1468353 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1469759 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1763683 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2033. Min Act: -0.0000

Data Index: 639704 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1991. Min Act: -0.0000

Data Index: 994976 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1536966 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1027498 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2034. Min Act: -0.0000

Data Index: 177870 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1384312 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2078. Min Act: -0.0000

Data Index: 777507 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1665168 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1076212 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1882. Min Act: -0.0000

Data Index: 992083 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1515661 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1862. Min Act: -0.0000

Data Index: 366369 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1233997 (The Pile)

Max Activating Token Index: 715