Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0001

Data Index: 500713 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1842. Min Act: -0.0001

Data Index: 630349 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1765. Min Act: -0.0001

Data Index: 102313 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1799. Min Act: -0.0001

Data Index: 159517 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1141799 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1709. Min Act: -0.0001

Data Index: 978958 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1574. Min Act: -0.0001

Data Index: 553019 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1633. Min Act: -0.0001

Data Index: 193256 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1648. Min Act: -0.0001

Data Index: 427533 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1643. Min Act: -0.0001

Data Index: 641829 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1540. Min Act: -0.0001

Data Index: 51197 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1096585 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1616. Min Act: -0.0001

Data Index: 323850 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1268142 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1602. Min Act: -0.0001

Data Index: 773368 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1595. Min Act: -0.0001

Data Index: 635235 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1281138 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1586. Min Act: -0.0001

Data Index: 814055 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1532. Min Act: -0.0001

Data Index: 482236 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1234241 (C4 (Web Text))

Max Activating Token Index: 1007