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

Dataset: The Pile

Neuron 1278 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: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1208262 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0766. Min Act: -0.0000

Data Index: 5318 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1479402 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1707191 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0894. Min Act: -0.0000

Data Index: 92014 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1576823 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1677831 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0786. Min Act: -0.0000

Data Index: 933442 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0873. Min Act: -0.0000

Data Index: 820338 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1374954 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1874017 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0833. Min Act: -0.0000

Data Index: 825790 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1681755 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1367792 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0746. Min Act: -0.0000

Data Index: 270616 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1508711 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1675755 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0763. Min Act: -0.0000

Data Index: 884804 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1854029 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1184127 (The Pile)

Max Activating Token Index: 963