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

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

Neuron 4449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1263160 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0555. Min Act: -0.0003

Data Index: 996555 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1053036 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0508. Min Act: -0.0003

Data Index: 589114 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0498. Min Act: -0.0003

Data Index: 704087 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0497. Min Act: -0.0003

Data Index: 400058 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0472. Min Act: -0.0003

Data Index: 788296 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0481. Min Act: -0.0003

Data Index: 95034 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0445. Min Act: -0.0003

Data Index: 375288 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1100691 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0446. Min Act: -0.0003

Data Index: 408664 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0430. Min Act: -0.0003

Data Index: 443777 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0443. Min Act: -0.0003

Data Index: 931068 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0431. Min Act: -0.0003

Data Index: 790662 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0433. Min Act: -0.0003

Data Index: 507459 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1296636 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0423. Min Act: -0.0003

Data Index: 693929 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0410. Min Act: -0.0003

Data Index: 478636 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0428. Min Act: -0.0003

Data Index: 632071 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1170895 (C4 (Web Text))

Max Activating Token Index: 260