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

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

Neuron 5387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1506876 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1648089 (Python Code)

Max Activating Token Index: 506

Text #2

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1431681 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1462424 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1188147 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1084885 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1597375 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1454482 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1638484 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0963. Min Act: -0.0000

Data Index: 887025 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1005. Min Act: -0.0001

Data Index: 532561 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1578962 (Python Code)

Max Activating Token Index: 615

Text #12

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1575452 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1585248 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1091. Min Act: -0.0000

Data Index: 431042 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1654463 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1592406 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1069493 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0886. Min Act: -0.0001

Data Index: 158062 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.1551. Min Range: -0.1551

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1409249 (Python Code)

Max Activating Token Index: 624