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

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

Neuron 188 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1918. Min Act: -0.0000

Data Index: 602378 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1870. Min Act: -0.0000

Data Index: 72947 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.2432. Min Act: -0.0000

Data Index: 257191 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.3578. Min Act: -0.0000

Data Index: 538509 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.2606. Min Act: -0.0000

Data Index: 742945 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1659. Min Act: -0.0000

Data Index: 71877 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1700. Min Act: -0.0000

Data Index: 476036 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1651. Min Act: -0.0000

Data Index: 364961 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1619462 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1596399 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0742. Min Act: -0.0000

Data Index: 690888 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1649040 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1641846 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1407987 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1601277 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1533215 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1462360 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1371264 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0113. Min Act: -0.0000

Data Index: 712869 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0983. Min Act: -0.0000

Data Index: 964985 (C4 (Web Text))

Max Activating Token Index: 294