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

Dataset: The Pile

Neuron 1748 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: 0.6580. Min Range: -0.6580

Max Act: 0.6580. Min Act: -0.0000

Data Index: 345160 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6154. Min Act: -0.0000

Data Index: 379439 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6223. Min Act: -0.0000

Data Index: 217281 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1086053 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1748686 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5607. Min Act: -0.0000

Data Index: 592427 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5144. Min Act: -0.0000

Data Index: 141074 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1073836 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5145. Min Act: -0.0000

Data Index: 654442 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4733. Min Act: -0.0000

Data Index: 859772 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1287941 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1746737 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1575460 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1243732 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4694. Min Act: -0.0000

Data Index: 315419 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4688. Min Act: -0.0000

Data Index: 588358 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1340973 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4607. Min Act: -0.0000

Data Index: 212119 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1356281 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1785786 (The Pile)

Max Activating Token Index: 294