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

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

Neuron 404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1046985 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0740. Min Act: -0.0000

Data Index: 349311 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1009921 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0670. Min Act: -0.0000

Data Index: 878241 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1031471 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0564. Min Act: -0.0000

Data Index: 59346 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0602. Min Act: -0.0000

Data Index: 167560 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0621. Min Act: -0.0000

Data Index: 352632 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1092875 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0605. Min Act: -0.0000

Data Index: 108788 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0558. Min Act: -0.0000

Data Index: 784797 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0594. Min Act: -0.0000

Data Index: 668390 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0512. Min Act: -0.0000

Data Index: 362982 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1155450 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0588. Min Act: -0.0000

Data Index: 443686 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0578. Min Act: -0.0000

Data Index: 368088 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1599 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0577. Min Act: -0.0000

Data Index: 332859 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0579. Min Act: -0.0000

Data Index: 826673 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.1380. Min Range: -0.1380

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1099334 (C4 (Web Text))

Max Activating Token Index: 91