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

Dataset: The Pile

Neuron 4057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.3076. Min Act: -0.0000

Data Index: 194110 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1402146 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.2543. Min Act: -0.0000

Data Index: 488363 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1846946 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1738093 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1503. Min Act: -0.0000

Data Index: 168915 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1203423 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1306201 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1561. Min Act: -0.0000

Data Index: 859967 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1068. Min Act: -0.0000

Data Index: 936363 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1415. Min Act: -0.0000

Data Index: 517991 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1774230 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1591514 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1424391 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1094008 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 1.3076. Min Range: -1.3076

Max Act: 0.9975. Min Act: -0.0000

Data Index: 57133 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1729844 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0611. Min Act: -0.0000

Data Index: 437883 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1391021 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1493596 (The Pile)

Max Activating Token Index: 86