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

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

Neuron 3359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0000

Data Index: 147438 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1223. Min Act: -0.0000

Data Index: 351358 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1294. Min Act: -0.0000

Data Index: 831718 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1140852 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1050186 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1187. Min Act: -0.0000

Data Index: 527604 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1123. Min Act: -0.0000

Data Index: 804335 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1144. Min Act: -0.0000

Data Index: 518877 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1163. Min Act: -0.0000

Data Index: 187903 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1062617 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1101. Min Act: -0.0000

Data Index: 258975 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1125. Min Act: -0.0000

Data Index: 377068 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1166. Min Act: -0.0000

Data Index: 550410 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1081. Min Act: -0.0000

Data Index: 628285 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1329453 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1070. Min Act: -0.0000

Data Index: 941605 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1001754 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1000. Min Act: -0.0001

Data Index: 205539 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1073364 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1144640 (C4 (Web Text))

Max Activating Token Index: 570