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

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

Neuron 1547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1182. Min Act: -0.0001

Data Index: 434125 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1529940 (Python Code)

Max Activating Token Index: 852

Text #2

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1493083 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1047. Min Act: -0.0001

Data Index: 70524 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0968. Min Act: -0.0001

Data Index: 517575 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1028. Min Act: -0.0001

Data Index: 264515 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0966. Min Act: -0.0001

Data Index: 568433 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1587971 (Python Code)

Max Activating Token Index: 120

Text #8

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1645609 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1066939 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0989. Min Act: -0.0001

Data Index: 950959 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1526045 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1425316 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1550082 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1034700 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0887. Min Act: -0.0001

Data Index: 356655 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1256877 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0890. Min Act: -0.0001

Data Index: 573478 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0851. Min Act: -0.0001

Data Index: 824796 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.1182. Min Range: -0.1182

Max Act: 0.0865. Min Act: -0.0001

Data Index: 316891 (C4 (Web Text))

Max Activating Token Index: 45