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

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

Neuron 3840 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: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1181623 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1521462 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1069. Min Act: -0.0000

Data Index: 156537 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1502968 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1451420 (Python Code)

Max Activating Token Index: 798

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1196. Min Act: -0.0001

Data Index: 3986 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1087. Min Act: -0.0000

Data Index: 751154 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1381037 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1452217 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1409265 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1587484 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0963. Min Act: -0.0000

Data Index: 525721 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1557967 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1561435 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1406342 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0931. Min Act: -0.0001

Data Index: 292268 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1438752 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1425665 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1595672 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0884. Min Act: -0.0000

Data Index: 65484 (C4 (Web Text))

Max Activating Token Index: 138