Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0003

Data Index: 673782 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1063. Min Act: -0.0004

Data Index: 1292451 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1006. Min Act: -0.0004

Data Index: 254089 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0961. Min Act: -0.0003

Data Index: 191193 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0967. Min Act: -0.0003

Data Index: 1048724 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0949. Min Act: -0.0004

Data Index: 952635 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1350616 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0918. Min Act: -0.0004

Data Index: 284110 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0921. Min Act: -0.0003

Data Index: 96896 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0958. Min Act: -0.0003

Data Index: 517956 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1082783 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0923. Min Act: -0.0003

Data Index: 1227939 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1014908 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1131589 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0883. Min Act: -0.0004

Data Index: 297380 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1348734 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1254404 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0894. Min Act: -0.0003

Data Index: 134473 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1128371 (C4 (Web Text))

Max Activating Token Index: 835