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

Dataset: The Pile

Neuron 1587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1633382 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3373. Min Act: -0.0000

Data Index: 543054 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1882420 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3755. Min Act: -0.0000

Data Index: 306965 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3272. Min Act: -0.0001

Data Index: 240468 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2994. Min Act: -0.0000

Data Index: 624131 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1889633 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1313764 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1383335 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2727. Min Act: -0.0000

Data Index: 26105 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2780. Min Act: -0.0000

Data Index: 904116 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2668. Min Act: -0.0000

Data Index: 803276 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2660. Min Act: -0.0000

Data Index: 968362 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1823081 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2799. Min Act: -0.0000

Data Index: 302841 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2481. Min Act: -0.0000

Data Index: 870485 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2511. Min Act: -0.0000

Data Index: 720871 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1342616 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1627071 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2561. Min Act: -0.0000

Data Index: 267391 (The Pile)

Max Activating Token Index: 590