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

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

Neuron 1700 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: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1135206 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1157664 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1129. Min Act: -0.0002

Data Index: 477964 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1019892 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1027. Min Act: -0.0002

Data Index: 455836 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1110. Min Act: -0.0002

Data Index: 768262 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1005. Min Act: -0.0002

Data Index: 693662 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1078. Min Act: -0.0002

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1036. Min Act: -0.0002

Data Index: 44605 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1029. Min Act: -0.0002

Data Index: 637056 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1110. Min Act: -0.0002

Data Index: 992387 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1018. Min Act: -0.0002

Data Index: 555430 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1002002 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1003. Min Act: -0.0002

Data Index: 192191 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1048. Min Act: -0.0002

Data Index: 147185 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1132810 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1002. Min Act: -0.0002

Data Index: 186672 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0948. Min Act: -0.0002

Data Index: 468988 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1072. Min Act: -0.0002

Data Index: 739419 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1028. Min Act: -0.0002

Data Index: 76659 (C4 (Web Text))

Max Activating Token Index: 482