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

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

Neuron 943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.1028. Min Act: -0.0000

Data Index: 151711 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0960. Min Act: -0.0000

Data Index: 896097 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0914. Min Act: -0.0000

Data Index: 897671 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1046997 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0951. Min Act: -0.0000

Data Index: 936708 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0853. Min Act: -0.0000

Data Index: 188103 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0867. Min Act: -0.0001

Data Index: 771098 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1611757 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0894. Min Act: -0.0000

Data Index: 855642 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0842. Min Act: -0.0001

Data Index: 757653 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0857. Min Act: -0.0000

Data Index: 909324 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1569633 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0803. Min Act: -0.0000

Data Index: 780829 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0860. Min Act: -0.0000

Data Index: 142355 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0861. Min Act: -0.0000

Data Index: 408130 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0803. Min Act: -0.0000

Data Index: 180103 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0861. Min Act: -0.0001

Data Index: 810826 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0806. Min Act: -0.0000

Data Index: 93330 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1589095 (Python Code)

Max Activating Token Index: 176

Text #19

Max Range: 0.1028. Min Range: -0.1028

Max Act: 0.0777. Min Act: -0.0000

Data Index: 98575 (C4 (Web Text))

Max Activating Token Index: 1014