Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2508 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.8599. Min Act: -0.0000

Data Index: 433654 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5501. Min Act: -0.0000

Data Index: 694071 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1392699 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1410072 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1820345 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1841119 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.5180. Min Act: -0.0001

Data Index: 332441 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4246. Min Act: -0.0000

Data Index: 748130 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4789. Min Act: -0.0000

Data Index: 672881 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.3679. Min Act: -0.0000

Data Index: 251918 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1858042 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1998011 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1671057 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.3708. Min Act: -0.0000

Data Index: 404062 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4326. Min Act: -0.0000

Data Index: 708993 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4555. Min Act: -0.0000

Data Index: 848919 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.3607. Min Act: -0.0000

Data Index: 760341 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1305091 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1667339 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.8599. Min Range: -0.8599

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1450820 (The Pile)

Max Activating Token Index: 966