Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1700 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.7563. Min Act: -0.0004

Data Index: 1612929 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6610. Min Act: -0.0004

Data Index: 1514781 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6777. Min Act: -0.0004

Data Index: 1464284 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6581. Min Act: -0.0004

Data Index: 1456048 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6259. Min Act: -0.0004

Data Index: 1445269 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6608. Min Act: -0.0004

Data Index: 1470593 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6194. Min Act: -0.0004

Data Index: 1409267 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6169. Min Act: -0.0004

Data Index: 1453057 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6569. Min Act: -0.0004

Data Index: 1385161 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6344. Min Act: -0.0004

Data Index: 1560648 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6341. Min Act: -0.0004

Data Index: 1380657 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5933. Min Act: -0.0004

Data Index: 1517486 (Python Code)

Max Activating Token Index: 374

Text #12

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6242. Min Act: -0.0004

Data Index: 1469041 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6426. Min Act: -0.0004

Data Index: 1486131 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6028. Min Act: -0.0004

Data Index: 1503257 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6184. Min Act: -0.0004

Data Index: 1576476 (Python Code)

Max Activating Token Index: 452

Text #16

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6369. Min Act: -0.0004

Data Index: 1532614 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6199. Min Act: -0.0004

Data Index: 1478224 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.5960. Min Act: -0.0004

Data Index: 1655407 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 0.7563. Min Range: -0.7563

Max Act: 0.6386. Min Act: -0.0004

Data Index: 1389829 (Python Code)

Max Activating Token Index: 568