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

Dataset: The Pile

Neuron 1832 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: 0.8539. Min Range: -0.8539

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1347804 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6988. Min Act: -0.0000

Data Index: 693010 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7405. Min Act: -0.0000

Data Index: 756046 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1423659 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1714644 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1514531 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1617582 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6473. Min Act: -0.0000

Data Index: 129093 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6771. Min Act: -0.0000

Data Index: 169243 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1409969 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1981844 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1773092 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1750996 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1011794 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6327. Min Act: -0.0000

Data Index: 705562 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1074140 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6631. Min Act: 0.0000

Data Index: 220023 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1580225 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1481458 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6357. Min Act: -0.0000

Data Index: 533993 (The Pile)

Max Activating Token Index: 408