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

Dataset: The Pile

Neuron 575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1189. Min Range: -1.1189

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1883207 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.1189. Min Range: -1.1189

Max Act: 1.1189. Min Act: -0.0000

Data Index: 309578 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.1189. Min Range: -1.1189

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1915130 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1584599 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.8142. Min Act: -0.0000

Data Index: 98239 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.8410. Min Act: -0.0000

Data Index: 510036 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1038533 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1110420 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1503447 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1486851 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1877989 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1383133 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1974167 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1478278 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1911174 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7523. Min Act: -0.0000

Data Index: 879678 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1139865 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1487235 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7535. Min Act: -0.0000

Data Index: 55619 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 1.1189. Min Range: -1.1189

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1271492 (The Pile)

Max Activating Token Index: 328