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

Dataset: The Pile

Neuron 1709 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0599. Min Range: -1.0599

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1589776 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.0599. Min Range: -1.0599

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1223253 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9657. Min Act: -0.0000

Data Index: 389390 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1287089 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9704. Min Act: -0.0000

Data Index: 583311 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9438. Min Act: 0.0000

Data Index: 160520 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1287315 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8838. Min Act: 0.0000

Data Index: 1789135 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1722141 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8302. Min Act: 0.0000

Data Index: 1100352 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8209. Min Act: 0.0000

Data Index: 1001337 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7590. Min Act: -0.0000

Data Index: 98482 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7607. Min Act: 0.0000

Data Index: 976283 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7561. Min Act: 0.0000

Data Index: 1269999 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1199406 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7871. Min Act: 0.0001

Data Index: 182408 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1669295 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7551. Min Act: 0.0000

Data Index: 56523 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7550. Min Act: 0.0000

Data Index: 1504674 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.7440. Min Act: 0.0000

Data Index: 1449844 (The Pile)

Max Activating Token Index: 39