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

Dataset: The Pile

Neuron 1345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1974219 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1521526 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1479183 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7174. Min Act: -0.0000

Data Index: 226221 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1842996 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6953. Min Act: -0.0000

Data Index: 141112 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1842738 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1103956 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1489570 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6679. Min Act: -0.0000

Data Index: 543846 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5652. Min Act: -0.0000

Data Index: 742743 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5349. Min Act: -0.0000

Data Index: 930446 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1839885 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1083803 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5538. Min Act: -0.0000

Data Index: 240442 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1071959 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5677. Min Act: -0.0000

Data Index: 296659 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1437774 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6094. Min Act: 0.0000

Data Index: 660652 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6943. Min Act: -0.0000

Data Index: 643780 (The Pile)

Max Activating Token Index: 1019