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

Dataset: The Pile

Neuron 1216 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: 0.2104. Min Range: -0.2104

Max Act: 0.2104. Min Act: -0.0000

Data Index: 784887 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1947. Min Act: -0.0000

Data Index: 408336 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.2036. Min Act: -0.0000

Data Index: 944019 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1925417 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1938. Min Act: -0.0000

Data Index: 265310 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1981612 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1068720 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1767. Min Act: -0.0000

Data Index: 990308 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1098722 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1837. Min Act: -0.0000

Data Index: 296440 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1482140 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1354065 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1699. Min Act: -0.0000

Data Index: 251018 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1799. Min Act: -0.0000

Data Index: 242890 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1862. Min Act: -0.0000

Data Index: 196439 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1917. Min Act: -0.0000

Data Index: 422934 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1664. Min Act: -0.0000

Data Index: 761550 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1641. Min Act: -0.0000

Data Index: 118587 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1617. Min Act: -0.0000

Data Index: 297320 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1471539 (The Pile)

Max Activating Token Index: 175