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

Dataset: The Pile

Neuron 727 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5873. Min Act: -0.0000

Data Index: 310694 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5502. Min Act: -0.0000

Data Index: 498849 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1212824 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1920527 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5589. Min Act: -0.0000

Data Index: 938271 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5022. Min Act: -0.0000

Data Index: 907822 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4079. Min Act: -0.0000

Data Index: 286195 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5090. Min Act: -0.0000

Data Index: 430695 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4551. Min Act: -0.0000

Data Index: 189617 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4991. Min Act: -0.0000

Data Index: 396658 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4840. Min Act: -0.0000

Data Index: 729765 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1524437 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1086715 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4498. Min Act: -0.0000

Data Index: 49589 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4460. Min Act: -0.0000

Data Index: 945446 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1650499 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4441. Min Act: -0.0000

Data Index: 887259 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1353815 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4064. Min Act: -0.0000

Data Index: 201930 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4557. Min Act: -0.0000

Data Index: 734348 (The Pile)

Max Activating Token Index: 690