Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1073 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1160604 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0748. Min Act: -0.0002

Data Index: 158606 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0697. Min Act: -0.0001

Data Index: 674703 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0631. Min Act: -0.0002

Data Index: 547251 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0659. Min Act: -0.0002

Data Index: 328516 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0638. Min Act: -0.0002

Data Index: 877697 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0656. Min Act: -0.0001

Data Index: 45411 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1349594 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0629. Min Act: -0.0002

Data Index: 41010 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1339647 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1120695 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0596. Min Act: -0.0002

Data Index: 523757 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0616. Min Act: -0.0001

Data Index: 503045 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0586. Min Act: -0.0001

Data Index: 868759 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0573. Min Act: -0.0002

Data Index: 599269 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0578. Min Act: -0.0001

Data Index: 918256 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0577. Min Act: -0.0002

Data Index: 489259 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1188098 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0548. Min Act: -0.0002

Data Index: 317986 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0562. Min Act: -0.0002

Data Index: 245721 (C4 (Web Text))

Max Activating Token Index: 301