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

Dataset: The Pile

Neuron 3650 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1078812 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1310400 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1708842 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2150. Min Act: -0.0000

Data Index: 273366 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.2087. Min Act: -0.0000

Data Index: 882934 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1209450 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1942. Min Act: -0.0000

Data Index: 44404 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1969. Min Act: -0.0000

Data Index: 664881 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1912. Min Act: -0.0000

Data Index: 323174 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1709. Min Act: -0.0000

Data Index: 175475 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1893141 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1579099 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1706086 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1860253 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1679. Min Act: -0.0000

Data Index: 246136 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1582. Min Act: -0.0000

Data Index: 614029 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1283183 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1668. Min Act: -0.0000

Data Index: 666867 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1999146 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.2640. Min Range: -0.2640

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1670380 (The Pile)

Max Activating Token Index: 545