Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0002

Data Index: 808294 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1103. Min Act: -0.0002

Data Index: 422686 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1078. Min Act: -0.0002

Data Index: 604074 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1011303 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1077. Min Act: -0.0002

Data Index: 853500 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1111973 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1059. Min Act: -0.0002

Data Index: 238020 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1071. Min Act: -0.0002

Data Index: 677840 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1072. Min Act: -0.0002

Data Index: 704025 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1010. Min Act: -0.0002

Data Index: 275068 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1063823 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0986. Min Act: -0.0002

Data Index: 705781 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0997. Min Act: -0.0002

Data Index: 442662 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0948. Min Act: -0.0002

Data Index: 166801 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0979. Min Act: -0.0002

Data Index: 26876 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0936. Min Act: -0.0002

Data Index: 717265 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1114134 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0901. Min Act: -0.0002

Data Index: 117600 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0920. Min Act: -0.0002

Data Index: 444 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0914. Min Act: -0.0002

Data Index: 68567 (C4 (Web Text))

Max Activating Token Index: 704