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

Dataset: The Pile

Neuron 1672 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: 1.9127. Min Range: -1.9127

Max Act: 1.9127. Min Act: -0.0000

Data Index: 826127 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.6317. Min Act: -0.0000

Data Index: 886919 (The Pile)

Max Activating Token Index: 805

Text #2

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1963887 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4578. Min Act: -0.0000

Data Index: 273698 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.5280. Min Act: -0.0000

Data Index: 1093024 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.5820. Min Act: -0.0000

Data Index: 347984 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1596489 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1882024 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1375494 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1983454 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4637. Min Act: -0.0000

Data Index: 868077 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1949918 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3663. Min Act: -0.0000

Data Index: 916831 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3929. Min Act: -0.0000

Data Index: 636249 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4722. Min Act: -0.0000

Data Index: 454537 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.2763. Min Act: -0.0000

Data Index: 474218 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.4028. Min Act: -0.0000

Data Index: 152162 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1514486 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3320. Min Act: -0.0000

Data Index: 644682 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1975357 (The Pile)

Max Activating Token Index: 405