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

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

Neuron 4645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0001

Data Index: 481450 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1173. Min Act: -0.0001

Data Index: 718445 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1158. Min Act: -0.0001

Data Index: 207096 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1141. Min Act: -0.0001

Data Index: 97735 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0997. Min Act: -0.0001

Data Index: 264313 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0979. Min Act: -0.0001

Data Index: 781611 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1042. Min Act: -0.0001

Data Index: 265243 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0975. Min Act: -0.0001

Data Index: 116712 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1329838 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1023. Min Act: -0.0001

Data Index: 872718 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0955. Min Act: -0.0001

Data Index: 745768 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1226860 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0962. Min Act: -0.0001

Data Index: 290436 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1033. Min Act: -0.0001

Data Index: 66044 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0925. Min Act: -0.0001

Data Index: 144679 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0904. Min Act: -0.0001

Data Index: 704333 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0991. Min Act: -0.0001

Data Index: 784404 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1050492 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0920. Min Act: -0.0001

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0931. Min Act: -0.0001

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 523