Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1042 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1137. Min Act: -0.0003

Data Index: 762105 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1180. Min Act: -0.0003

Data Index: 280864 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1096699 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1131. Min Act: -0.0003

Data Index: 49021 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1099. Min Act: -0.0003

Data Index: 116202 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1078. Min Act: -0.0003

Data Index: 299180 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1101. Min Act: -0.0003

Data Index: 1336236 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1100. Min Act: -0.0003

Data Index: 258669 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1009. Min Act: -0.0003

Data Index: 1319503 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1119. Min Act: -0.0003

Data Index: 388679 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1113. Min Act: -0.0003

Data Index: 122227 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1099. Min Act: -0.0003

Data Index: 136282 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1051. Min Act: -0.0003

Data Index: 761105 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1052. Min Act: -0.0003

Data Index: 1103267 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1034. Min Act: -0.0003

Data Index: 1211206 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1027. Min Act: -0.0003

Data Index: 777206 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1108. Min Act: -0.0003

Data Index: 1224560 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1024. Min Act: -0.0003

Data Index: 617544 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0987. Min Act: -0.0003

Data Index: 693904 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1041. Min Act: -0.0003

Data Index: 95227 (C4 (Web Text))

Max Activating Token Index: 266