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

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

Neuron 246 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: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1497755 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0785. Min Act: -0.0002

Data Index: 198495 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1397839 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0728. Min Act: -0.0002

Data Index: 344934 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1615918 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0716. Min Act: -0.0002

Data Index: 115698 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1564857 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0697. Min Act: -0.0002

Data Index: 749487 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0687. Min Act: -0.0002

Data Index: 803397 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1148896 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0645. Min Act: -0.0002

Data Index: 973324 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1635359 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0644. Min Act: -0.0002

Data Index: 185606 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1635562 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1427535 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1513453 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0645. Min Act: -0.0002

Data Index: 884829 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0640. Min Act: -0.0002

Data Index: 858515 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0615. Min Act: -0.0002

Data Index: 716176 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1339492 (C4 (Web Text))

Max Activating Token Index: 660