Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1073. Min Act: -0.0002

Data Index: 318368 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1011209 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1020. Min Act: -0.0002

Data Index: 980470 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1027. Min Act: -0.0002

Data Index: 884270 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1024. Min Act: -0.0001

Data Index: 344868 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0982. Min Act: -0.0002

Data Index: 833326 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1175201 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1040912 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0930. Min Act: -0.0002

Data Index: 77599 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1066205 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0863. Min Act: -0.0002

Data Index: 146940 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0882. Min Act: -0.0002

Data Index: 208399 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1261296 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0904. Min Act: -0.0002

Data Index: 585078 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1015860 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1007899 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1023733 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1209742 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1359205 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0883. Min Act: -0.0000

Data Index: 745091 (C4 (Web Text))

Max Activating Token Index: 892