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

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

Neuron 254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1311353 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0002

Data Index: 1285260 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1325820 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1097900 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1781. Min Act: -0.0002

Data Index: 381515 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1210357 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1102214 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1487. Min Act: -0.0002

Data Index: 120260 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1447. Min Act: -0.0001

Data Index: 758898 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1578. Min Act: -0.0002

Data Index: 713754 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1779. Min Act: -0.0002

Data Index: 172074 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1604. Min Act: -0.0002

Data Index: 1276838 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1604. Min Act: -0.0002

Data Index: 1275009 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1655. Min Act: -0.0001

Data Index: 980330 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1521. Min Act: -0.0001

Data Index: 257047 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1535. Min Act: -0.0001

Data Index: 361799 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1685. Min Act: -0.0001

Data Index: 843290 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1559. Min Act: -0.0002

Data Index: 393811 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1497. Min Act: -0.0002

Data Index: 1054203 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1108968 (C4 (Web Text))

Max Activating Token Index: 889