Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.2772. Min Act: -0.0000

Data Index: 70444 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1955. Min Act: -0.0000

Data Index: 743939 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1829. Min Act: -0.0000

Data Index: 279722 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.1391. Min Act: -0.0000

Data Index: 43002 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1085768 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0175. Min Act: -0.0000

Data Index: 561268 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0565. Min Act: -0.0000

Data Index: 180189 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0795. Min Act: -0.0000

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9946. Min Act: -0.0000

Data Index: 792319 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.2772. Min Range: -1.2772

Max Act: 1.0431. Min Act: -0.0000

Data Index: 134427 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9244. Min Act: -0.0000

Data Index: 27551 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1123902 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.8252. Min Act: -0.0000

Data Index: 656370 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.8578. Min Act: -0.0000

Data Index: 164850 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9714. Min Act: -0.0000

Data Index: 871381 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1343507 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1085134 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.8935. Min Act: -0.0000

Data Index: 942976 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9116. Min Act: -0.0000

Data Index: 910902 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.2772. Min Range: -1.2772

Max Act: 0.9120. Min Act: -0.0000

Data Index: 183292 (C4 (Web Text))

Max Activating Token Index: 920