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

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

Neuron 3437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1533247 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1603525 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1471043 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1551011 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1431753 (Python Code)

Max Activating Token Index: 199

Text #5

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1499834 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1567386 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1010. Min Act: -0.0000

Data Index: 835438 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1470455 (Python Code)

Max Activating Token Index: 517

Text #9

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1435993 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1419662 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1478945 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1603320 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1562158 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1459817 (Python Code)

Max Activating Token Index: 939

Text #15

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1438230 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1389168 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1651480 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1578865 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 0.1329. Min Range: -0.1329

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1561982 (Python Code)

Max Activating Token Index: 21