Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3716 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0002

Data Index: 554177 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1158. Min Act: -0.0002

Data Index: 575578 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1168. Min Act: -0.0002

Data Index: 475108 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1137. Min Act: -0.0002

Data Index: 900351 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1135022 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1131. Min Act: -0.0002

Data Index: 494117 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1125. Min Act: -0.0003

Data Index: 191854 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1092. Min Act: -0.0002

Data Index: 202282 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1094. Min Act: -0.0002

Data Index: 409423 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1092. Min Act: -0.0002

Data Index: 53149 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1085. Min Act: -0.0002

Data Index: 473036 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1088. Min Act: -0.0003

Data Index: 1298264 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1066726 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1077. Min Act: -0.0002

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1095. Min Act: -0.0002

Data Index: 791712 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1087. Min Act: -0.0002

Data Index: 405588 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1317737 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1153771 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1067. Min Act: -0.0002

Data Index: 875054 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1142127 (C4 (Web Text))

Max Activating Token Index: 199