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

Dataset: The Pile

Neuron 107 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: 0.1060. Min Range: -0.1060

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1232177 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1030. Min Act: -0.0000

Data Index: 459426 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1853599 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1098209 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1973105 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0978. Min Act: -0.0000

Data Index: 66761 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1318491 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1011578 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0918. Min Act: -0.0000

Data Index: 943098 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0964. Min Act: -0.0000

Data Index: 930462 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0901. Min Act: -0.0000

Data Index: 511142 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0961. Min Act: -0.0000

Data Index: 785518 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1484510 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1288708 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1649511 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1918031 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0938. Min Act: -0.0000

Data Index: 385667 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1263107 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1423742 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0883. Min Act: -0.0000

Data Index: 319815 (The Pile)

Max Activating Token Index: 142