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

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

Neuron 735 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.9690. Min Act: -0.0000

Data Index: 331587 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1234825 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.8630. Min Act: -0.0000

Data Index: 394978 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7928. Min Act: -0.0000

Data Index: 586013 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1197060 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7819. Min Act: -0.0000

Data Index: 69738 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7641. Min Act: -0.0000

Data Index: 575538 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7369. Min Act: -0.0000

Data Index: 549235 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1045887 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6013. Min Act: -0.0000

Data Index: 188208 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6855. Min Act: -0.0000

Data Index: 1120499 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.5836. Min Act: -0.0000

Data Index: 32535 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7770. Min Act: -0.0000

Data Index: 1067587 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6681. Min Act: -0.0000

Data Index: 420563 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6732. Min Act: -0.0000

Data Index: 133675 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6620. Min Act: -0.0000

Data Index: 1079139 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.5690. Min Act: -0.0000

Data Index: 78169 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7653. Min Act: -0.0000

Data Index: 265809 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.6349. Min Act: -0.0000

Data Index: 421241 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.9690. Min Range: -1.9690

Max Act: 1.7066. Min Act: -0.0000

Data Index: 646156 (C4 (Web Text))

Max Activating Token Index: 201