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

Dataset: The Pile

Neuron 1579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1128066 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.4243. Min Act: -0.0000

Data Index: 813065 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1017147 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1222269 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1126159 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1186545 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3472. Min Act: 0.0000

Data Index: 1563984 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3640. Min Act: -0.0000

Data Index: 35537 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1576438 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3258. Min Act: -0.0000

Data Index: 113116 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.3685. Min Act: -0.0000

Data Index: 503816 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2676. Min Act: -0.0000

Data Index: 638284 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1579159 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2992. Min Act: -0.0000

Data Index: 857630 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2981. Min Act: -0.0000

Data Index: 331757 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1421814 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2893. Min Act: -0.0000

Data Index: 110244 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1544547 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1209713 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 0.5849. Min Range: -0.5849

Max Act: 0.2842. Min Act: -0.0000

Data Index: 41479 (The Pile)

Max Activating Token Index: 297