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

Dataset: The Pile

Neuron 1745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6959. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1154440 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1277361 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1726260 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1110149 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1386606 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6359. Min Act: -0.0000

Data Index: 954685 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1797412 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1857863 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1081148 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1232226 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1278599 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1118950 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1140589 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1533147 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4753. Min Act: -0.0000

Data Index: 377458 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1075967 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4796. Min Act: -0.0000

Data Index: 858507 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.4421. Min Act: -0.0000

Data Index: 263624 (The Pile)

Max Activating Token Index: 38