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

Dataset: The Pile

Neuron 759 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0790. Min Act: -0.0000

Data Index: 58879 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0001

Data Index: 171989 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1696742 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9650. Min Act: -0.0000

Data Index: 631313 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1838343 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8536. Min Act: -0.0000

Data Index: 597725 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1240088 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1115602 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9024. Min Act: -0.0000

Data Index: 547058 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1526783 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1099774 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1873378 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8843. Min Act: -0.0000

Data Index: 360285 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9035. Min Act: -0.0000

Data Index: 334600 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1211150 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1738469 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8149. Min Act: -0.0000

Data Index: 719205 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8617. Min Act: -0.0000

Data Index: 651354 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1396074 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1067524 (The Pile)

Max Activating Token Index: 264