Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1084 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0002

Data Index: 814201 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0987. Min Act: -0.0002

Data Index: 686037 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0932. Min Act: -0.0002

Data Index: 964304 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0951. Min Act: -0.0002

Data Index: 781402 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0938. Min Act: -0.0002

Data Index: 891125 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1418590 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0896. Min Act: -0.0002

Data Index: 117425 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0880. Min Act: -0.0002

Data Index: 107778 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1221811 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0823. Min Act: -0.0002

Data Index: 431790 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0833. Min Act: -0.0002

Data Index: 545115 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1967774 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1231734 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0823. Min Act: -0.0002

Data Index: 505179 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1293870 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0811. Min Act: -0.0002

Data Index: 825049 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0796. Min Act: -0.0002

Data Index: 584912 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1806959 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1511751 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1786076 (The Pile)

Max Activating Token Index: 111