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

Dataset: The Pile

Neuron 3376 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: 1.2789. Min Range: -1.2789

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1228012 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1801. Min Act: -0.0000

Data Index: 307928 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0947. Min Act: -0.0000

Data Index: 349356 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1634460 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1460128 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0522. Min Act: -0.0000

Data Index: 22385 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0494. Min Act: -0.0000

Data Index: 562729 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0411. Min Act: -0.0001

Data Index: 301976 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1081265 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1500592 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9689. Min Act: -0.0000

Data Index: 565017 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1113887 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1375826 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1813228 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9923. Min Act: -0.0000

Data Index: 768008 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1824553 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9142. Min Act: -0.0000

Data Index: 963844 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9606. Min Act: -0.0000

Data Index: 440949 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9164. Min Act: -0.0000

Data Index: 122604 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1852474 (The Pile)

Max Activating Token Index: 788