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

Dataset: The Pile

Neuron 2237 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: 1.8766. Min Range: -1.8766

Max Act: 1.8766. Min Act: -0.0000

Data Index: 1241756 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1911817 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.7706. Min Act: -0.0000

Data Index: 97052 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.7531. Min Act: -0.0000

Data Index: 1072106 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1991538 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.6647. Min Act: -0.0000

Data Index: 221203 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.6142. Min Act: -0.0000

Data Index: 1200793 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1874807 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4614. Min Act: -0.0000

Data Index: 559851 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.6223. Min Act: -0.0000

Data Index: 383056 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1749001 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1053377 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4077. Min Act: -0.0000

Data Index: 256891 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1150127 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1533968 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4475. Min Act: -0.0000

Data Index: 6942 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1760077 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.3452. Min Act: -0.0000

Data Index: 839743 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.4286. Min Act: -0.0000

Data Index: 865094 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 1.8766. Min Range: -1.8766

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1628787 (The Pile)

Max Activating Token Index: 82