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

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

Neuron 1404 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: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0002

Data Index: 16374 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1112. Min Act: -0.0002

Data Index: 693821 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0993. Min Act: -0.0002

Data Index: 734741 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0921. Min Act: -0.0002

Data Index: 180361 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1133672 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0963. Min Act: -0.0002

Data Index: 804834 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0979. Min Act: -0.0002

Data Index: 982983 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0930. Min Act: -0.0002

Data Index: 369771 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1074614 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0914. Min Act: -0.0002

Data Index: 811038 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0892. Min Act: -0.0002

Data Index: 580429 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0812. Min Act: -0.0002

Data Index: 246654 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1320210 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0797. Min Act: -0.0002

Data Index: 504324 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0858. Min Act: -0.0002

Data Index: 817152 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0820. Min Act: -0.0002

Data Index: 460156 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1036031 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0881. Min Act: -0.0002

Data Index: 560095 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0785. Min Act: -0.0002

Data Index: 837468 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0800. Min Act: -0.0002

Data Index: 518615 (C4 (Web Text))

Max Activating Token Index: 207