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

Dataset: The Pile

Neuron 1089 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: 0.2098. Min Range: -0.2098

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1045813 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1991803 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1949. Min Act: -0.0000

Data Index: 923678 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1802. Min Act: -0.0000

Data Index: 434208 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1368328 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1802. Min Act: -0.0000

Data Index: 89263 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1144197 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1087256 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1832080 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1964466 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1618. Min Act: -0.0000

Data Index: 156561 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1628. Min Act: -0.0000

Data Index: 654801 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1613553 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1779748 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1815325 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1638. Min Act: -0.0000

Data Index: 147051 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1685669 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1489477 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1591687 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1420261 (The Pile)

Max Activating Token Index: 975