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

Dataset: The Pile

Neuron 2353 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.7041. Min Act: -0.0000

Data Index: 437661 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.6192. Min Act: -0.0000

Data Index: 67323 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1794837 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.6112. Min Act: -0.0000

Data Index: 764960 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1319752 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5724. Min Act: -0.0000

Data Index: 493154 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5867. Min Act: -0.0000

Data Index: 499624 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1783016 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1371451 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1513502 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1122020 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.5492. Min Act: -0.0000

Data Index: 968750 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1703825 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4868. Min Act: -0.0000

Data Index: 822275 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4947. Min Act: -0.0000

Data Index: 4871 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1699295 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1621772 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4785. Min Act: -0.0000

Data Index: 236978 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4567. Min Act: -0.0000

Data Index: 380315 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.7041. Min Range: -0.7041

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1850409 (The Pile)

Max Activating Token Index: 653