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

Dataset: The Pile

Neuron 2838 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1523035 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6229. Min Act: -0.0000

Data Index: 93402 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1951557 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1750266 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1116684 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5459. Min Act: -0.0000

Data Index: 605947 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5703. Min Act: -0.0000

Data Index: 756165 (The Pile)

Max Activating Token Index: 158

Text #7

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4986. Min Act: -0.0000

Data Index: 606267 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5127. Min Act: -0.0000

Data Index: 820087 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5063. Min Act: -0.0000

Data Index: 959113 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5244. Min Act: -0.0000

Data Index: 855091 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5188. Min Act: -0.0000

Data Index: 469958 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1243013 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4931. Min Act: -0.0000

Data Index: 249928 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1700324 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4878. Min Act: -0.0000

Data Index: 856524 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5059. Min Act: -0.0000

Data Index: 708646 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1410709 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1593465 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.4804. Min Act: -0.0000

Data Index: 826282 (The Pile)

Max Activating Token Index: 38