Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4875 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1418830 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1606156 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1487641 (Python Code)

Max Activating Token Index: 808

Text #3

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5832. Min Act: -0.0000

Data Index: 353748 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1401105 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.6258. Min Act: -0.0000

Data Index: 338337 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5567. Min Act: -0.0000

Data Index: 318259 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1390384 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1369989 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1574405 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1008503 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1231396 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1436799 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1650861 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5278. Min Act: -0.0000

Data Index: 270318 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5294. Min Act: -0.0000

Data Index: 321208 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1650802 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1649249 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1138486 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.7262. Min Range: -0.7262

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1368317 (Python Code)

Max Activating Token Index: 242