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

Dataset: The Pile

Neuron 3505 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6154. Min Act: -0.0000

Data Index: 896519 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5261. Min Act: -0.0000

Data Index: 947744 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1772704 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0000

Data Index: 573893 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6217. Min Act: -0.0000

Data Index: 955697 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1166116 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1030360 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1378472 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1466141 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5455. Min Act: -0.0000

Data Index: 998275 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5306. Min Act: -0.0000

Data Index: 715933 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1286375 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1849780 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5155. Min Act: -0.0000

Data Index: 2680 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1988682 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1623597 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1760545 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4424. Min Act: -0.0000

Data Index: 688350 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1321626 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4711. Min Act: -0.0000

Data Index: 293834 (The Pile)

Max Activating Token Index: 160