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

Dataset: The Pile

Neuron 105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1866535 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7357. Min Act: -0.0000

Data Index: 247393 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1238647 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1807609 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6696. Min Act: -0.0000

Data Index: 508416 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1734705 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6765. Min Act: -0.0000

Data Index: 906730 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5702. Min Act: -0.0000

Data Index: 451107 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1366315 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1155221 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7076. Min Act: -0.0000

Data Index: 783109 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6940. Min Act: -0.0000

Data Index: 246213 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7582. Min Act: -0.0000

Data Index: 287883 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6759. Min Act: -0.0000

Data Index: 35906 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1461859 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1381599 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7239. Min Act: -0.0000

Data Index: 405748 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1591929 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1270449 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6358. Min Act: -0.0000

Data Index: 427263 (The Pile)

Max Activating Token Index: 816