Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2048. Min Act: -0.0001

Data Index: 825624 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2111. Min Act: -0.0001

Data Index: 155709 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1993. Min Act: -0.0001

Data Index: 979189 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1979. Min Act: -0.0001

Data Index: 645027 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1901. Min Act: -0.0001

Data Index: 1174257 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1909. Min Act: -0.0001

Data Index: 996955 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1850. Min Act: -0.0001

Data Index: 251788 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1890. Min Act: -0.0001

Data Index: 84154 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1799. Min Act: -0.0001

Data Index: 292239 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1448670 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1423405 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1678. Min Act: -0.0001

Data Index: 1544449 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1535373 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1522223 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1799. Min Act: -0.0001

Data Index: 828102 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1783. Min Act: -0.0001

Data Index: 486311 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1783. Min Act: -0.0001

Data Index: 626947 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1548802 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1410644 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1496219 (Python Code)

Max Activating Token Index: 695