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

Dataset: The Pile

Neuron 2636 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: 1.1613. Min Range: -1.1613

Max Act: 1.1613. Min Act: -0.0000

Data Index: 539737 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 1.1613. Min Range: -1.1613

Max Act: 1.1215. Min Act: -0.0000

Data Index: 605678 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1954099 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1309993 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1389263 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7771. Min Act: -0.0000

Data Index: 700106 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7710. Min Act: -0.0000

Data Index: 565095 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1736924 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8858. Min Act: -0.0000

Data Index: 590735 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1717477 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1483983 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1371798 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1735210 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1383126 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1510872 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1393031 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1848812 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7081. Min Act: -0.0000

Data Index: 584232 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.7032. Min Act: -0.0000

Data Index: 223963 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.1613. Min Range: -1.1613

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1576400 (The Pile)

Max Activating Token Index: 76