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

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

Neuron 4452 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.6742. Min Act: -0.0000

Data Index: 746515 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1332677 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5626. Min Act: -0.0000

Data Index: 36494 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4860. Min Act: -0.0000

Data Index: 641880 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4913. Min Act: -0.0000

Data Index: 681674 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.5030. Min Act: -0.0000

Data Index: 703067 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1167026 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4848. Min Act: -0.0000

Data Index: 429209 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4645. Min Act: -0.0000

Data Index: 286947 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4625. Min Act: -0.0000

Data Index: 527976 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1339941 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1156167 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4521. Min Act: -0.0000

Data Index: 897949 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4543. Min Act: -0.0000

Data Index: 369411 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4497. Min Act: -0.0000

Data Index: 398863 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1126448 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4339. Min Act: -0.0000

Data Index: 737890 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4299. Min Act: -0.0000

Data Index: 891883 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1063759 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.6899. Min Range: -0.6899

Max Act: 0.4099. Min Act: -0.0000

Data Index: 750688 (C4 (Web Text))

Max Activating Token Index: 749