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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1892. Min Range: -1.1892

Max Act: 1.1892. Min Act: -0.0000

Data Index: 334903 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.1892. Min Range: -1.1892

Max Act: 1.1214. Min Act: -0.0000

Data Index: 954060 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.1892. Min Range: -1.1892

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1174712 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.1892. Min Range: -1.1892

Max Act: 1.0198. Min Act: -0.0000

Data Index: 458030 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.1892. Min Range: -1.1892

Max Act: 1.0416. Min Act: -0.0000

Data Index: 867434 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.9733. Min Act: -0.0000

Data Index: 200317 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1000009 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.9138. Min Act: -0.0000

Data Index: 591729 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1345540 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8919. Min Act: -0.0000

Data Index: 959060 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8734. Min Act: -0.0000

Data Index: 241338 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8735. Min Act: -0.0000

Data Index: 491111 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8465. Min Act: -0.0000

Data Index: 847332 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8800. Min Act: -0.0000

Data Index: 184858 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7705. Min Act: -0.0000

Data Index: 493645 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8563. Min Act: -0.0000

Data Index: 580201 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8187. Min Act: -0.0000

Data Index: 978573 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.7740. Min Act: -0.0000

Data Index: 811715 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8355. Min Act: -0.0000

Data Index: 781504 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.1892. Min Range: -1.1892

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1496069 (Python Code)

Max Activating Token Index: 171