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

Dataset: The Pile

Neuron 1250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.8799. Min Act: -0.0000

Data Index: 686273 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7986. Min Act: -0.0000

Data Index: 705776 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1336911 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.8340. Min Act: -0.0000

Data Index: 632830 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1879796 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1360793 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1919707 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1897880 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7900. Min Act: -0.0000

Data Index: 937522 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6918. Min Act: -0.0000

Data Index: 113179 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7071. Min Act: -0.0000

Data Index: 722620 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1909068 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1460189 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7345. Min Act: -0.0000

Data Index: 200621 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1405557 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1234829 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1165298 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1950173 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6040. Min Act: -0.0000

Data Index: 564833 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 0.9217. Min Range: -0.9217

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1773905 (The Pile)

Max Activating Token Index: 517