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

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

Neuron 1683 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: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0003

Data Index: 892528 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0756. Min Act: -0.0003

Data Index: 651087 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0753. Min Act: -0.0004

Data Index: 189856 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0705. Min Act: -0.0004

Data Index: 1226720 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0660. Min Act: -0.0003

Data Index: 373126 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1201901 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0685. Min Act: -0.0004

Data Index: 703083 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0683. Min Act: -0.0003

Data Index: 703589 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1259636 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0671. Min Act: -0.0003

Data Index: 529933 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0682. Min Act: -0.0004

Data Index: 513446 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0638. Min Act: -0.0003

Data Index: 964836 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1084792 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0640. Min Act: -0.0003

Data Index: 16398 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0668. Min Act: -0.0003

Data Index: 139702 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0650. Min Act: -0.0004

Data Index: 403274 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0662. Min Act: -0.0003

Data Index: 321235 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0630. Min Act: -0.0003

Data Index: 650952 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0633. Min Act: -0.0003

Data Index: 543587 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0640. Min Act: -0.0004

Data Index: 488260 (C4 (Web Text))

Max Activating Token Index: 295