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

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

Neuron 165 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: 8.5086. Min Range: -8.5086

Max Act: 8.5086. Min Act: -0.0001

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 8.5086. Min Range: -8.5086

Max Act: 8.0732. Min Act: -0.0001

Data Index: 1098741 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.7427. Min Act: -0.0001

Data Index: 993552 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.9524. Min Act: -0.0001

Data Index: 889146 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.7546. Min Act: -0.0001

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.7213. Min Act: -0.0001

Data Index: 255684 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.9788. Min Act: -0.0001

Data Index: 1174414 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.1797. Min Act: -0.0001

Data Index: 536609 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.2288. Min Act: -0.0001

Data Index: 701092 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.7547. Min Act: -0.0001

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.3984. Min Act: -0.0001

Data Index: 586168 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.4028. Min Act: -0.0001

Data Index: 330873 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.5306. Min Act: -0.0001

Data Index: 612942 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.0437. Min Act: -0.0001

Data Index: 820255 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.6824. Min Act: -0.0001

Data Index: 567164 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.5992. Min Act: -0.0001

Data Index: 1281177 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.7275. Min Act: -0.0001

Data Index: 354385 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 8.5086. Min Range: -8.5086

Max Act: 6.9645. Min Act: -0.0001

Data Index: 835318 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.1633. Min Act: -0.0001

Data Index: 671929 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 8.5086. Min Range: -8.5086

Max Act: 7.1563. Min Act: -0.0001

Data Index: 531071 (C4 (Web Text))

Max Activating Token Index: 823