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

Dataset: The Pile

Neuron 2695 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: 0.2714. Min Range: -0.2714

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1609357 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1825064 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2551. Min Act: -0.0000

Data Index: 681110 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1874960 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2369. Min Act: -0.0000

Data Index: 618756 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2435. Min Act: -0.0000

Data Index: 842094 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1040731 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1221525 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1239928 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1427218 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2072. Min Act: -0.0000

Data Index: 394782 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1997451 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2169. Min Act: -0.0000

Data Index: 89036 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1247062 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1338791 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2160. Min Act: -0.0000

Data Index: 606957 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1967562 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1618886 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1967. Min Act: -0.0000

Data Index: 188950 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1241343 (The Pile)

Max Activating Token Index: 275