Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1080 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0003

Data Index: 477253 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0597. Min Act: -0.0004

Data Index: 352408 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0573. Min Act: -0.0003

Data Index: 555241 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1558071 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0591. Min Act: -0.0002

Data Index: 969397 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1626785 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1496076 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1366887 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1464897 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0576. Min Act: -0.0004

Data Index: 1348647 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0548. Min Act: -0.0004

Data Index: 239205 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1621218 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1408079 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1401842 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1644292 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1505916 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1480942 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1588345 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1423142 (Python Code)

Max Activating Token Index: 609

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1536284 (Python Code)

Max Activating Token Index: 770