Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1426460 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0783. Min Act: -0.0002

Data Index: 503202 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0753. Min Act: -0.0002

Data Index: 586526 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1194019 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0595. Min Act: -0.0002

Data Index: 546125 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1239146 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1302131 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0586. Min Act: -0.0002

Data Index: 695256 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1234078 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1037023 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0628. Min Act: -0.0002

Data Index: 871225 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0628. Min Act: -0.0002

Data Index: 585021 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0618. Min Act: -0.0002

Data Index: 23425 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1080997 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0472. Min Act: -0.0002

Data Index: 950199 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1086291 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1272088 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0585. Min Act: -0.0002

Data Index: 64555 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0631. Min Act: -0.0002

Data Index: 986890 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0593. Min Act: -0.0002

Data Index: 658789 (C4 (Web Text))

Max Activating Token Index: 199