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

Dataset: The Pile

Neuron 1866 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1243595 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1209185 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1550753 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4949. Min Act: -0.0000

Data Index: 46579 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1564148 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1743879 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1032899 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1079777 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3783. Min Act: -0.0000

Data Index: 174556 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1547971 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3907. Min Act: -0.0000

Data Index: 287815 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1352705 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3891. Min Act: -0.0000

Data Index: 875554 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3874. Min Act: -0.0000

Data Index: 626767 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3825. Min Act: -0.0000

Data Index: 185690 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3932. Min Act: -0.0000

Data Index: 332209 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3738. Min Act: -0.0000

Data Index: 103469 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3804. Min Act: -0.0000

Data Index: 297982 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3810. Min Act: -0.0000

Data Index: 39214 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 0.6214. Min Range: -0.6214

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1620086 (The Pile)

Max Activating Token Index: 530