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

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

Neuron 36 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1083840 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1317. Min Act: -0.0001

Data Index: 900805 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1221. Min Act: -0.0001

Data Index: 955566 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1136. Min Act: -0.0001

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1380. Min Act: -0.0001

Data Index: 285762 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1309703 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1104. Min Act: -0.0001

Data Index: 75168 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1174. Min Act: -0.0001

Data Index: 403535 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1107. Min Act: -0.0001

Data Index: 441596 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1010. Min Act: -0.0001

Data Index: 291225 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1123. Min Act: -0.0001

Data Index: 149991 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1158. Min Act: -0.0001

Data Index: 182717 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1147. Min Act: -0.0001

Data Index: 158103 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1192. Min Act: -0.0001

Data Index: 616026 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1081. Min Act: -0.0001

Data Index: 614723 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1080. Min Act: -0.0001

Data Index: 721685 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1009457 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1290304 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1142. Min Act: -0.0001

Data Index: 893890 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1062. Min Act: -0.0001

Data Index: 759246 (C4 (Web Text))

Max Activating Token Index: 73