Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 260 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0002

Data Index: 666361 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1582020 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0952. Min Act: -0.0002

Data Index: 824110 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0966. Min Act: -0.0002

Data Index: 598138 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0942. Min Act: -0.0002

Data Index: 809502 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0972. Min Act: -0.0002

Data Index: 257510 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1992213 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1294064 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0960. Min Act: -0.0002

Data Index: 405270 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1148192 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0950. Min Act: -0.0002

Data Index: 376539 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0933. Min Act: -0.0002

Data Index: 341614 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0948. Min Act: -0.0002

Data Index: 447105 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1727883 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0883. Min Act: -0.0002

Data Index: 759130 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0899. Min Act: -0.0002

Data Index: 862765 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1811183 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0892. Min Act: -0.0002

Data Index: 102155 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1659848 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0910. Min Act: -0.0002

Data Index: 692193 (The Pile)

Max Activating Token Index: 595