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

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

Neuron 2198 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: 1.8133. Min Range: -1.8133

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1395482 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1431778 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1543880 (Python Code)

Max Activating Token Index: 555

Text #3

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1393182 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1558916 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1591936 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1454496 (Python Code)

Max Activating Token Index: 512

Text #7

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1520914 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4227. Min Act: -0.0000

Data Index: 1386994 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1583210 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1628491 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1370964 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1620964 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5257. Min Act: -0.0000

Data Index: 1393284 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1598992 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1630625 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1373729 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1478538 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.5239. Min Act: -0.0000

Data Index: 1605010 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 1.8133. Min Range: -1.8133

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1574596 (Python Code)

Max Activating Token Index: 616