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

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

Neuron 2229 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: 0.2596. Min Range: -0.2596

Max Act: 0.2596. Min Act: -0.0000

Data Index: 964531 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1604958 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1581955 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1609114 (Python Code)

Max Activating Token Index: 226

Text #4

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1484625 (Python Code)

Max Activating Token Index: 199

Text #5

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1483262 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1395024 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1448238 (Python Code)

Max Activating Token Index: 541

Text #8

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1643482 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1396498 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1449725 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1534682 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1577082 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1610635 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2089. Min Act: -0.0000

Data Index: 823421 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1460803 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1443875 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1627893 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1606206 (Python Code)

Max Activating Token Index: 590

Text #19

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1636366 (Python Code)

Max Activating Token Index: 825