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

Dataset: The Pile

Neuron 958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.9054. Min Act: -0.0000

Data Index: 960714 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1044878 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1441202 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1126907 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6731. Min Act: -0.0000

Data Index: 160744 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7100. Min Act: -0.0000

Data Index: 918514 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1207419 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1475303 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6758. Min Act: -0.0000

Data Index: 612680 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1811630 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1013290 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6623. Min Act: -0.0000

Data Index: 866677 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1491305 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1710901 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6237. Min Act: -0.0000

Data Index: 712108 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6423. Min Act: -0.0000

Data Index: 721758 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1518770 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1393375 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1777358 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6255. Min Act: -0.0000

Data Index: 574795 (The Pile)

Max Activating Token Index: 305