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

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

Neuron 4803 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3034. Min Range: -1.3034

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1532046 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 1.3034. Min Range: -1.3034

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1524777 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 1.3034. Min Range: -1.3034

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1426110 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 1.3034. Min Range: -1.3034

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1593860 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1061394 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1561845 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1431270 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1490912 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.9070. Min Act: -0.0000

Data Index: 315799 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1613170 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8304. Min Act: -0.0000

Data Index: 445338 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1251986 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1369388 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1488896 (Python Code)

Max Activating Token Index: 1008

Text #14

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1469997 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1510363 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1624295 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8036. Min Act: -0.0000

Data Index: 931160 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1626307 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 1.3034. Min Range: -1.3034

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1368912 (Python Code)

Max Activating Token Index: 922