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

Dataset: The Pile

Neuron 228 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: 0.2987. Min Range: -0.2987

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1663086 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1392783 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1210506 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2880. Min Act: -0.0000

Data Index: 546378 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2370. Min Act: -0.0000

Data Index: 934792 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1454225 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1413597 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1724777 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1887790 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2134. Min Act: -0.0000

Data Index: 564647 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2110. Min Act: -0.0000

Data Index: 999310 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1831630 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2027. Min Act: -0.0000

Data Index: 913316 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1687277 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2092. Min Act: -0.0000

Data Index: 748572 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1992. Min Act: -0.0000

Data Index: 37154 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.2040. Min Act: -0.0000

Data Index: 947074 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1940. Min Act: -0.0000

Data Index: 718725 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1829287 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.2987. Min Range: -0.2987

Max Act: 0.1902. Min Act: -0.0000

Data Index: 561609 (The Pile)

Max Activating Token Index: 236