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

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

Neuron 5129 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1534251 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7824. Min Act: -0.0000

Data Index: 579767 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1644060 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1531969 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1512607 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1478196 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1450640 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1443637 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1486179 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1500506 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1645795 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5909. Min Act: -0.0000

Data Index: 580134 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1572753 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1370449 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1456846 (Python Code)

Max Activating Token Index: 766

Text #15

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1600606 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1619778 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1538109 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1539891 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1379170 (Python Code)

Max Activating Token Index: 755