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

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

Neuron 4062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1212040 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1289. Min Act: -0.0001

Data Index: 901174 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1205730 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1114. Min Act: -0.0001

Data Index: 593200 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0958. Min Act: -0.0001

Data Index: 936998 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1074. Min Act: -0.0001

Data Index: 334266 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1069035 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0894. Min Act: -0.0001

Data Index: 161803 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1218351 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1260953 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0856. Min Act: -0.0001

Data Index: 342044 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0940. Min Act: -0.0001

Data Index: 477792 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0861. Min Act: -0.0001

Data Index: 827455 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1077455 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1178387 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0824. Min Act: -0.0001

Data Index: 451205 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0858. Min Act: -0.0001

Data Index: 590662 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0902. Min Act: -0.0000

Data Index: 868949 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1237940 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0877. Min Act: -0.0001

Data Index: 88850 (C4 (Web Text))

Max Activating Token Index: 452