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

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

Neuron 4060 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1474495 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1058726 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1580358 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1638796 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1435982 (Python Code)

Max Activating Token Index: 627

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1448211 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0882. Min Act: -0.0003

Data Index: 542095 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1562606 (Python Code)

Max Activating Token Index: 867

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0864. Min Act: -0.0003

Data Index: 763708 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1586290 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1626698 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1609426 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1371073 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1410689 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1491243 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0823. Min Act: -0.0003

Data Index: 459395 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0820. Min Act: -0.0003

Data Index: 472408 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1442193 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0812. Min Act: -0.0002

Data Index: 100440 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1617743 (Python Code)

Max Activating Token Index: 163