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

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

Neuron 1598 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: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0001

Data Index: 114 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1152035 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0941. Min Act: -0.0001

Data Index: 179571 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1295470 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1645673 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0796. Min Act: -0.0001

Data Index: 310971 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0820. Min Act: -0.0001

Data Index: 277974 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0783. Min Act: -0.0001

Data Index: 222975 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1237280 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0818. Min Act: -0.0001

Data Index: 985447 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0769. Min Act: -0.0001

Data Index: 907255 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1122455 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0765. Min Act: -0.0001

Data Index: 769137 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0706. Min Act: -0.0002

Data Index: 792163 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0704. Min Act: -0.0001

Data Index: 598586 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0714. Min Act: -0.0001

Data Index: 987935 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0736. Min Act: -0.0002

Data Index: 74861 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0709. Min Act: -0.0001

Data Index: 904604 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1482341 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.0682. Min Act: -0.0001

Data Index: 468364 (C4 (Web Text))

Max Activating Token Index: 583