Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 926 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 704852 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1230. Min Act: -0.0000

Data Index: 596132 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1085104 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1262538 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1153. Min Act: -0.0000

Data Index: 971321 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1071. Min Act: -0.0000

Data Index: 719397 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1290588 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1066. Min Act: -0.0000

Data Index: 338911 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1046. Min Act: -0.0000

Data Index: 743940 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1027. Min Act: -0.0000

Data Index: 927367 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0983. Min Act: -0.0000

Data Index: 923236 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1022565 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1028. Min Act: -0.0000

Data Index: 512767 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1170206 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0913. Min Act: -0.0000

Data Index: 246788 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0873. Min Act: -0.0000

Data Index: 428347 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0927. Min Act: -0.0000

Data Index: 618936 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0892. Min Act: -0.0000

Data Index: 23973 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1345981 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.0911. Min Act: -0.0000

Data Index: 719951 (C4 (Web Text))

Max Activating Token Index: 569