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

Dataset: The Pile

Neuron 2958 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: 1.0764. Min Range: -1.0764

Max Act: 1.0756. Min Act: -0.0000

Data Index: 523046 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0605. Min Act: -0.0000

Data Index: 570018 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1680921 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.0764. Min Range: -1.0764

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1121350 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9881. Min Act: -0.0001

Data Index: 1682695 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1887253 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1920929 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9938. Min Act: -0.0000

Data Index: 280710 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1968194 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9174. Min Act: -0.0000

Data Index: 287436 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8437. Min Act: -0.0000

Data Index: 21673 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.9178. Min Act: -0.0000

Data Index: 127845 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7951. Min Act: -0.0000

Data Index: 251931 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1080426 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1997847 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1317253 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7841. Min Act: -0.0000

Data Index: 245075 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1020685 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1025281 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.0764. Min Range: -1.0764

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1954925 (The Pile)

Max Activating Token Index: 309