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

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

Neuron 1283 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1129570 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2459. Min Act: -0.0000

Data Index: 494950 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1098478 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2035. Min Act: -0.0000

Data Index: 102938 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1253292 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1969. Min Act: -0.0000

Data Index: 989511 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1977. Min Act: -0.0000

Data Index: 275828 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1823. Min Act: -0.0000

Data Index: 799725 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1683. Min Act: -0.0000

Data Index: 421395 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1759. Min Act: -0.0000

Data Index: 302182 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1043737 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1687. Min Act: -0.0000

Data Index: 63394 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1740. Min Act: -0.0000

Data Index: 542678 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1226262 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1711. Min Act: -0.0000

Data Index: 311385 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1647. Min Act: -0.0000

Data Index: 913295 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1635. Min Act: -0.0000

Data Index: 550481 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1161794 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1523. Min Act: -0.0000

Data Index: 706495 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1454. Min Act: -0.0000

Data Index: 448028 (C4 (Web Text))

Max Activating Token Index: 762