Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1515 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1172279 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1110358 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1615768 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1519576 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0693. Min Act: -0.0001

Data Index: 377690 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1187078 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1294440 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1470857 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1564365 (Python Code)

Max Activating Token Index: 656

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1402190 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0621. Min Act: -0.0001

Data Index: 811195 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0616. Min Act: -0.0001

Data Index: 642520 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0634. Min Act: -0.0001

Data Index: 847686 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1169071 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1451585 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0621. Min Act: -0.0001

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1550203 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0603. Min Act: -0.0001

Data Index: 691592 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0575. Min Act: -0.0001

Data Index: 210860 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1454991 (Python Code)

Max Activating Token Index: 875