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

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

Neuron 1925 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: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1110057 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1188. Min Act: -0.0002

Data Index: 222713 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1170. Min Act: -0.0002

Data Index: 836280 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1151. Min Act: -0.0002

Data Index: 673038 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1129. Min Act: -0.0002

Data Index: 364568 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1157. Min Act: -0.0002

Data Index: 890342 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1151. Min Act: -0.0002

Data Index: 560547 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1193. Min Act: -0.0002

Data Index: 351164 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1137. Min Act: -0.0002

Data Index: 11445 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1119. Min Act: -0.0002

Data Index: 911575 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1038598 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1062. Min Act: -0.0002

Data Index: 137597 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1111. Min Act: -0.0001

Data Index: 639289 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1098. Min Act: -0.0002

Data Index: 260555 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1080. Min Act: -0.0002

Data Index: 358541 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1083. Min Act: -0.0002

Data Index: 148963 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1219513 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1205011 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1153. Min Act: -0.0002

Data Index: 331868 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1049. Min Act: -0.0002

Data Index: 409122 (C4 (Web Text))

Max Activating Token Index: 738