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

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

Neuron 635 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: 0.0737. Min Range: -0.0737

Max Act: 0.0733. Min Act: -0.0004

Data Index: 522809 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0003

Data Index: 245243 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0726. Min Act: -0.0003

Data Index: 633377 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0707. Min Act: -0.0003

Data Index: 524559 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0702. Min Act: -0.0003

Data Index: 733247 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0667. Min Act: -0.0003

Data Index: 481987 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1299505 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0682. Min Act: -0.0003

Data Index: 63489 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1204271 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0656. Min Act: -0.0003

Data Index: 359538 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1144718 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0646. Min Act: -0.0004

Data Index: 731554 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0642. Min Act: -0.0003

Data Index: 134877 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0634. Min Act: -0.0003

Data Index: 391041 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0655. Min Act: -0.0003

Data Index: 815017 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0657. Min Act: -0.0003

Data Index: 60113 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0644. Min Act: -0.0003

Data Index: 785962 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0630. Min Act: -0.0004

Data Index: 168513 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0639. Min Act: -0.0003

Data Index: 141395 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0638. Min Act: -0.0003

Data Index: 16404 (C4 (Web Text))

Max Activating Token Index: 460