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

Dataset: The Pile

Neuron 1403 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: 1.0714. Min Range: -1.0714

Max Act: 1.0448. Min Act: -0.0000

Data Index: 71770 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0714. Min Act: -0.0000

Data Index: 755613 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1534860 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0002. Min Act: -0.0000

Data Index: 250877 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1421540 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1910159 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9610. Min Act: -0.0000

Data Index: 71572 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0034. Min Act: -0.0000

Data Index: 947510 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1179127 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1737968 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9752. Min Act: -0.0000

Data Index: 867975 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9123. Min Act: -0.0000

Data Index: 69278 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8819. Min Act: -0.0000

Data Index: 204256 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9511. Min Act: -0.0000

Data Index: 314247 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1185050 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9784. Min Act: -0.0000

Data Index: 584034 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9679. Min Act: -0.0000

Data Index: 216951 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9306. Min Act: -0.0000

Data Index: 208282 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9537. Min Act: -0.0000

Data Index: 550731 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9848. Min Act: -0.0000

Data Index: 721967 (The Pile)

Max Activating Token Index: 180