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

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

Neuron 1007 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: 1.1148. Min Range: -1.1148

Max Act: 1.1148. Min Act: -0.0001

Data Index: 704566 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9816. Min Act: -0.0001

Data Index: 882605 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9603. Min Act: -0.0001

Data Index: 729514 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1310048 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8009. Min Act: -0.0001

Data Index: 225421 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8146. Min Act: -0.0001

Data Index: 797797 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8396. Min Act: -0.0001

Data Index: 168695 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8095. Min Act: -0.0001

Data Index: 976061 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8274. Min Act: -0.0001

Data Index: 23095 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8458. Min Act: -0.0001

Data Index: 1083380 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8635. Min Act: -0.0001

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8854. Min Act: -0.0001

Data Index: 693157 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7925. Min Act: -0.0001

Data Index: 925173 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7469. Min Act: -0.0001

Data Index: 1014381 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8322. Min Act: -0.0001

Data Index: 1212377 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7807. Min Act: -0.0001

Data Index: 953998 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8074. Min Act: -0.0001

Data Index: 3378 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.8082. Min Act: -0.0001

Data Index: 685727 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1088657 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.1148. Min Range: -1.1148

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1083491 (C4 (Web Text))

Max Activating Token Index: 996