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

Dataset: The Pile

Neuron 1385 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 431441 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1026289 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1689779 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0780. Min Act: -0.0002

Data Index: 698588 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0806. Min Act: -0.0002

Data Index: 482197 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0778. Min Act: -0.0002

Data Index: 607922 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1403586 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0735. Min Act: -0.0002

Data Index: 569633 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0702. Min Act: -0.0002

Data Index: 181727 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1040511 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0708. Min Act: -0.0002

Data Index: 116738 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0700. Min Act: -0.0002

Data Index: 841630 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1265035 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1518123 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0623. Min Act: -0.0002

Data Index: 945770 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1949087 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1814622 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1748871 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1493696 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1022195 (The Pile)

Max Activating Token Index: 770