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

Dataset: The Pile

Neuron 4219 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: 0.2905. Min Range: -0.2905

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1902974 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2706. Min Act: -0.0000

Data Index: 331009 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2678. Min Act: -0.0000

Data Index: 810499 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1805162 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1172776 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2243. Min Act: -0.0000

Data Index: 622574 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2392. Min Act: -0.0000

Data Index: 291219 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1489557 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1253858 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1902498 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2125. Min Act: -0.0000

Data Index: 47074 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1907. Min Act: -0.0000

Data Index: 163195 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1927931 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2068. Min Act: -0.0000

Data Index: 859232 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1799772 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1451866 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1237578 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2048. Min Act: -0.0000

Data Index: 334773 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1953. Min Act: -0.0000

Data Index: 522003 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1888. Min Act: -0.0000

Data Index: 704761 (The Pile)

Max Activating Token Index: 917