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

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

Neuron 4566 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: 4.1581. Min Range: -4.1581

Max Act: 4.1581. Min Act: -0.0000

Data Index: 285719 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9620. Min Act: -0.0000

Data Index: 102869 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 4.1581. Min Range: -4.1581

Max Act: 4.1299. Min Act: -0.0000

Data Index: 118809 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.9988. Min Act: -0.0000

Data Index: 926650 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.8919. Min Act: -0.0000

Data Index: 702799 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.5332. Min Act: -0.0000

Data Index: 1227814 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.6475. Min Act: -0.0000

Data Index: 1343223 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.4796. Min Act: -0.0000

Data Index: 581888 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.3749. Min Act: 0.0000

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.1691. Min Act: -0.0000

Data Index: 906767 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.0487. Min Act: 0.0000

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.3399. Min Act: -0.0000

Data Index: 1141816 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.1710. Min Act: -0.0000

Data Index: 1521071 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.0712. Min Act: -0.0000

Data Index: 203816 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 4.1581. Min Range: -4.1581

Max Act: 3.2229. Min Act: -0.0000

Data Index: 885786 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 4.1581. Min Range: -4.1581

Max Act: 2.8799. Min Act: -0.0000

Data Index: 800705 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 4.1581. Min Range: -4.1581

Max Act: 2.9753. Min Act: -0.0000

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 4.1581. Min Range: -4.1581

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1523925 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 4.1581. Min Range: -4.1581

Max Act: 2.6191. Min Act: -0.0000

Data Index: 1486227 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 4.1581. Min Range: -4.1581

Max Act: 2.7505. Min Act: -0.0000

Data Index: 216591 (C4 (Web Text))

Max Activating Token Index: 951