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

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

Neuron 2338 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1253. Min Act: -0.0004

Data Index: 17756 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1202. Min Act: -0.0004

Data Index: 780893 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1118. Min Act: -0.0004

Data Index: 346839 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1114. Min Act: -0.0004

Data Index: 510215 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1093. Min Act: -0.0004

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1041. Min Act: -0.0004

Data Index: 352812 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1080. Min Act: -0.0004

Data Index: 1261163 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1155. Min Act: -0.0004

Data Index: 964828 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0004

Data Index: 1236715 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1063. Min Act: -0.0004

Data Index: 1194886 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1099. Min Act: -0.0004

Data Index: 315565 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1018. Min Act: -0.0004

Data Index: 609965 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1045. Min Act: -0.0004

Data Index: 227654 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1154. Min Act: -0.0004

Data Index: 1245326 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1030. Min Act: -0.0004

Data Index: 481309 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1057. Min Act: -0.0004

Data Index: 652859 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1064. Min Act: -0.0004

Data Index: 938754 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1090. Min Act: -0.0004

Data Index: 1198595 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1169. Min Act: -0.0004

Data Index: 785628 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1050. Min Act: -0.0004

Data Index: 1262453 (C4 (Web Text))

Max Activating Token Index: 274