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

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

Neuron 1774 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0005

Data Index: 820839 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1254. Min Act: -0.0005

Data Index: 1072695 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1103. Min Act: -0.0005

Data Index: 680406 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1062. Min Act: -0.0005

Data Index: 234691 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0992. Min Act: -0.0005

Data Index: 202448 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1012. Min Act: -0.0005

Data Index: 22057 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1000. Min Act: -0.0005

Data Index: 47909 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0937. Min Act: -0.0005

Data Index: 1291483 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0951. Min Act: -0.0005

Data Index: 377655 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0931. Min Act: -0.0005

Data Index: 1315794 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0906. Min Act: -0.0004

Data Index: 32051 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0913. Min Act: -0.0005

Data Index: 394846 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0899. Min Act: -0.0005

Data Index: 484645 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0894. Min Act: -0.0005

Data Index: 311799 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0918. Min Act: -0.0005

Data Index: 149431 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0887. Min Act: -0.0005

Data Index: 877097 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0843. Min Act: -0.0005

Data Index: 894077 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0875. Min Act: -0.0005

Data Index: 145946 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0868. Min Act: -0.0005

Data Index: 37288 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0872. Min Act: -0.0005

Data Index: 645151 (C4 (Web Text))

Max Activating Token Index: 437