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

Dataset: The Pile

Neuron 409 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: 1.1873. Min Range: -1.1873

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1098632 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0102. Min Act: -0.0000

Data Index: 675812 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1858299 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9797. Min Act: -0.0000

Data Index: 358815 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9488. Min Act: -0.0000

Data Index: 264856 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1231484 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1635952 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1770248 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1366141 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9656. Min Act: -0.0000

Data Index: 724786 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9410. Min Act: -0.0000

Data Index: 187966 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9080. Min Act: -0.0000

Data Index: 503835 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9023. Min Act: -0.0000

Data Index: 525250 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9653. Min Act: -0.0000

Data Index: 956938 (The Pile)

Max Activating Token Index: 957

Text #14

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1979626 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8891. Min Act: -0.0000

Data Index: 245304 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1123039 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1795371 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1720942 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.9289. Min Act: -0.0000

Data Index: 265574 (The Pile)

Max Activating Token Index: 295