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

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

Neuron 3583 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.8761. Min Act: -0.0000

Data Index: 269366 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1117949 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.7618. Min Act: -0.0000

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1307272 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1027089 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1570694 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.6107. Min Act: -0.0000

Data Index: 538459 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1054509 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1079471 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.5365. Min Act: -0.0000

Data Index: 452620 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1321586 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.5362. Min Act: -0.0000

Data Index: 487611 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4858. Min Act: -0.0000

Data Index: 615902 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1210088 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4868. Min Act: -0.0000

Data Index: 232818 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1079590 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4966. Min Act: -0.0000

Data Index: 841208 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4587. Min Act: -0.0000

Data Index: 111888 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4704. Min Act: -0.0000

Data Index: 871446 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.8761. Min Range: -0.8761

Max Act: 0.4678. Min Act: -0.0000

Data Index: 551542 (C4 (Web Text))

Max Activating Token Index: 386