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

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

Neuron 2526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2354. Min Act: -0.0000

Data Index: 625684 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2346. Min Act: -0.0000

Data Index: 587816 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2178. Min Act: -0.0000

Data Index: 274824 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1977. Min Act: -0.0000

Data Index: 361010 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1861. Min Act: -0.0000

Data Index: 324743 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1918. Min Act: -0.0000

Data Index: 675857 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1942. Min Act: -0.0000

Data Index: 882699 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1209689 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1933. Min Act: -0.0000

Data Index: 469380 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1155435 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1775. Min Act: -0.0000

Data Index: 621027 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1264908 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1755. Min Act: -0.0000

Data Index: 907786 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1910. Min Act: -0.0000

Data Index: 442243 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1708. Min Act: -0.0000

Data Index: 251005 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1211591 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1593. Min Act: -0.0000

Data Index: 975747 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1784. Min Act: -0.0000

Data Index: 88969 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1674. Min Act: -0.0000

Data Index: 554923 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1708. Min Act: -0.0000

Data Index: 590663 (C4 (Web Text))

Max Activating Token Index: 249