Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0000

Data Index: 925443 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0891. Min Act: -0.0000

Data Index: 643784 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0990. Min Act: -0.0000

Data Index: 832643 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1887899 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0832. Min Act: -0.0000

Data Index: 795319 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1320375 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0805. Min Act: -0.0000

Data Index: 149091 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1103244 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0710. Min Act: -0.0000

Data Index: 36354 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0715. Min Act: -0.0000

Data Index: 64763 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1031851 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1591041 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1047997 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0709. Min Act: -0.0000

Data Index: 580608 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1647661 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1381113 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0620. Min Act: -0.0000

Data Index: 893474 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1352244 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0560. Min Act: -0.0000

Data Index: 776165 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1764115 (The Pile)

Max Activating Token Index: 995