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

Dataset: The Pile

Neuron 875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.1955. Min Act: -0.0000

Data Index: 235506 (The Pile)

Max Activating Token Index: 336

Text #1

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.0334. Min Act: -0.0000

Data Index: 935140 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9955. Min Act: -0.0000

Data Index: 753606 (The Pile)

Max Activating Token Index: 678

Text #3

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1552734 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9837. Min Act: -0.0000

Data Index: 303936 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9574. Min Act: -0.0000

Data Index: 701199 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1088412 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9671. Min Act: -0.0000

Data Index: 332830 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1743781 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9074. Min Act: -0.0000

Data Index: 81006 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9476. Min Act: -0.0000

Data Index: 392797 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8794. Min Act: -0.0000

Data Index: 686168 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1579916 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1683879 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1304633 (The Pile)

Max Activating Token Index: 272

Text #15

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1968466 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1299542 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 1.1955. Min Range: -1.1955

Max Act: 1.0095. Min Act: -0.0000

Data Index: 728132 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9176. Min Act: -0.0000

Data Index: 1709455 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.1955. Min Range: -1.1955

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1119157 (The Pile)

Max Activating Token Index: 972