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

Dataset: The Pile

Neuron 4264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1902768 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1442358 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2285. Min Act: -0.0000

Data Index: 901905 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1819906 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2136. Min Act: -0.0000

Data Index: 245876 (The Pile)

Max Activating Token Index: 307

Text #5

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1992. Min Act: -0.0000

Data Index: 935622 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2098. Min Act: -0.0000

Data Index: 726919 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.2086. Min Act: -0.0000

Data Index: 412276 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1884134 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1696393 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1878. Min Act: -0.0000

Data Index: 31527 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1738. Min Act: -0.0000

Data Index: 655359 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1498858 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1843. Min Act: -0.0000

Data Index: 717212 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1725. Min Act: -0.0000

Data Index: 753673 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1717604 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1502. Min Act: -0.0000

Data Index: 686773 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1695. Min Act: -0.0000

Data Index: 718261 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1673. Min Act: -0.0000

Data Index: 319831 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.2338. Min Range: -0.2338

Max Act: 0.1734. Min Act: -0.0000

Data Index: 23093 (The Pile)

Max Activating Token Index: 955