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

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

Neuron 274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1044. Min Act: -0.0001

Data Index: 962375 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1009. Min Act: -0.0001

Data Index: 926697 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0001

Data Index: 731143 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1007. Min Act: -0.0001

Data Index: 508075 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0928. Min Act: -0.0001

Data Index: 752580 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1179223 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0930. Min Act: -0.0001

Data Index: 702599 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0965. Min Act: -0.0001

Data Index: 526985 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0877. Min Act: -0.0001

Data Index: 150985 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0892. Min Act: -0.0002

Data Index: 143299 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0934. Min Act: -0.0001

Data Index: 794156 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1190138 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0871. Min Act: -0.0001

Data Index: 235209 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1242555 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0841. Min Act: -0.0001

Data Index: 141236 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1171986 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0967. Min Act: -0.0001

Data Index: 735026 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1014905 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1001088 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1050948 (C4 (Web Text))

Max Activating Token Index: 21