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

Dataset: The Pile

Neuron 504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0919. Min Act: -0.0002

Data Index: 262140 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1553328 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0948. Min Act: -0.0002

Data Index: 865086 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0889. Min Act: -0.0002

Data Index: 188488 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0964. Min Act: -0.0001

Data Index: 642746 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1644776 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0831. Min Act: -0.0002

Data Index: 388487 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0883. Min Act: -0.0001

Data Index: 888481 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1664406 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0872. Min Act: -0.0002

Data Index: 594999 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1336320 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0838. Min Act: -0.0001

Data Index: 783465 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1676903 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0858. Min Act: -0.0001

Data Index: 578440 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1909734 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0893. Min Act: -0.0002

Data Index: 829337 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1919077 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0847. Min Act: -0.0002

Data Index: 68273 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1394117 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0835. Min Act: -0.0001

Data Index: 155394 (The Pile)

Max Activating Token Index: 953