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

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

Neuron 2063 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.9702. Min Act: -0.0000

Data Index: 1312955 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.9136. Min Act: -0.0000

Data Index: 854802 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.7476. Min Act: -0.0000

Data Index: 205692 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.8115. Min Act: -0.0000

Data Index: 486305 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.9129. Min Act: -0.0000

Data Index: 1256403 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1358700 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.7201. Min Act: -0.0000

Data Index: 27308 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.8073. Min Act: -0.0000

Data Index: 736705 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.7198. Min Act: -0.0000

Data Index: 777188 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1064347 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.6424. Min Act: -0.0000

Data Index: 22603 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1337137 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.4603. Min Act: -0.0000

Data Index: 358179 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.5307. Min Act: 0.0000

Data Index: 42581 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.5215. Min Act: 0.0001

Data Index: 91917 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.5580. Min Act: -0.0000

Data Index: 401116 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.4155. Min Act: -0.0000

Data Index: 198034 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.6196. Min Act: -0.0000

Data Index: 765589 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.4340. Min Act: -0.0000

Data Index: 83698 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.9702. Min Range: -1.9702

Max Act: 1.4677. Min Act: -0.0000

Data Index: 1292490 (C4 (Web Text))

Max Activating Token Index: 699