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

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

Neuron 3801 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: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 30717 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1187359 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 345873 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 280186 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1171980 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0002

Data Index: 297739 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1002722 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0002

Data Index: 190488 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1204432 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1133262 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0094. Min Act: -0.0002

Data Index: 470809 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1153258 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0094. Min Act: -0.0002

Data Index: 661925 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0002

Data Index: 928617 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0077. Min Act: -0.0002

Data Index: 929349 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0002

Data Index: 665181 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0086. Min Act: -0.0002

Data Index: 912759 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0097. Min Act: -0.0002

Data Index: 813373 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0002

Data Index: 853136 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0083. Min Act: -0.0002

Data Index: 702353 (C4 (Web Text))

Max Activating Token Index: 747