Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7692. Min Act: -0.0000

Data Index: 92496 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1985721 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7734. Min Act: -0.0000

Data Index: 532873 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1458824 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6603. Min Act: -0.0000

Data Index: 797801 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1683802 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1733801 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1380424 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1283489 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6807. Min Act: -0.0000

Data Index: 737361 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7028. Min Act: -0.0000

Data Index: 927530 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1059991 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6826. Min Act: -0.0000

Data Index: 845002 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1720558 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6916. Min Act: -0.0000

Data Index: 859281 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1954326 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1456466 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1728351 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.6125. Min Act: -0.0000

Data Index: 972448 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 0.8172. Min Range: -0.8172

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1516251 (The Pile)

Max Activating Token Index: 759