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

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

Neuron 4143 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1227377 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1005617 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0827. Min Act: -0.0000

Data Index: 852630 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0765. Min Act: -0.0000

Data Index: 65897 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0803. Min Act: -0.0000

Data Index: 927507 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0708. Min Act: -0.0000

Data Index: 7251 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1160233 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0680. Min Act: -0.0000

Data Index: 961169 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0652. Min Act: -0.0000

Data Index: 315787 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0668. Min Act: -0.0000

Data Index: 596505 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0649. Min Act: -0.0000

Data Index: 148138 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0664. Min Act: 0.0000

Data Index: 1211815 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1065903 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0668. Min Act: -0.0000

Data Index: 398106 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0614. Min Act: -0.0000

Data Index: 920132 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0589. Min Act: -0.0000

Data Index: 779619 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0580. Min Act: -0.0000

Data Index: 695895 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0542. Min Act: -0.0000

Data Index: 491715 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0555. Min Act: -0.0000

Data Index: 611357 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0541. Min Act: -0.0000

Data Index: 514370 (C4 (Web Text))

Max Activating Token Index: 541