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

Dataset: The Pile

Neuron 1613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2785. Min Act: -0.0000

Data Index: 953350 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1068543 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1046417 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1806736 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2062. Min Act: -0.0000

Data Index: 110517 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2359. Min Act: -0.0000

Data Index: 97282 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1857. Min Act: -0.0000

Data Index: 356869 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2126. Min Act: -0.0000

Data Index: 987121 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1874267 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2199. Min Act: -0.0000

Data Index: 266460 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1711. Min Act: -0.0000

Data Index: 1001621 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1826996 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1896519 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1704. Min Act: -0.0000

Data Index: 762887 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1436. Min Act: -0.0000

Data Index: 759122 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1821049 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1818990 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1391402 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1420. Min Act: -0.0000

Data Index: 202535 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1483908 (The Pile)

Max Activating Token Index: 624