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

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

Neuron 1963 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2521. Min Act: -0.0003

Data Index: 1315859 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1202061 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1967. Min Act: -0.0002

Data Index: 816631 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1957. Min Act: -0.0003

Data Index: 1270037 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1976. Min Act: -0.0002

Data Index: 181739 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1909. Min Act: -0.0003

Data Index: 399528 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1910. Min Act: -0.0003

Data Index: 61696 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1817. Min Act: -0.0003

Data Index: 824536 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1765. Min Act: -0.0003

Data Index: 1267717 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1773. Min Act: -0.0003

Data Index: 965472 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1713. Min Act: -0.0003

Data Index: 154767 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1829. Min Act: -0.0003

Data Index: 1295328 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1767. Min Act: -0.0002

Data Index: 1079170 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1785. Min Act: -0.0003

Data Index: 1208452 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1726. Min Act: -0.0003

Data Index: 336548 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1670. Min Act: -0.0002

Data Index: 580377 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1735. Min Act: -0.0002

Data Index: 897303 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1668. Min Act: -0.0003

Data Index: 50319 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1719. Min Act: -0.0002

Data Index: 247077 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1725. Min Act: -0.0003

Data Index: 266507 (C4 (Web Text))

Max Activating Token Index: 351