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

Dataset: The Pile

Neuron 2226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1718191 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8890. Min Act: -0.0000

Data Index: 432973 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1804051 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.8026. Min Act: -0.0000

Data Index: 666741 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1601730 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1874147 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6557. Min Act: -0.0000

Data Index: 189783 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1482375 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1225263 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6613. Min Act: -0.0000

Data Index: 86129 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6648. Min Act: -0.0000

Data Index: 781335 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1229562 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1396309 (The Pile)

Max Activating Token Index: 422

Text #13

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1992884 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.5947. Min Act: -0.0000

Data Index: 504311 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1455083 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1099740 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1492923 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.6325. Min Act: -0.0000

Data Index: 28557 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 0.9802. Min Range: -0.9802

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1208769 (The Pile)

Max Activating Token Index: 1000