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

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

Neuron 4598 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8903. Min Act: 0.0000

Data Index: 995408 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.8011. Min Act: -0.0000

Data Index: 700363 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6868. Min Act: -0.0000

Data Index: 23886 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1320632 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5854. Min Act: -0.0000

Data Index: 891403 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5626. Min Act: -0.0000

Data Index: 950135 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1276887 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5423. Min Act: -0.0000

Data Index: 643885 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5238. Min Act: -0.0000

Data Index: 826899 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1258622 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5112. Min Act: -0.0000

Data Index: 482323 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4885. Min Act: -0.0000

Data Index: 689382 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5019. Min Act: -0.0000

Data Index: 663595 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5015. Min Act: 0.0000

Data Index: 1155365 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4770. Min Act: -0.0000

Data Index: 743492 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4756. Min Act: -0.0000

Data Index: 784623 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4547. Min Act: -0.0000

Data Index: 979833 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4661. Min Act: -0.0000

Data Index: 794659 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4534. Min Act: -0.0000

Data Index: 548544 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1305736 (C4 (Web Text))

Max Activating Token Index: 894