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

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

Neuron 4875 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1370601 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1389257 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1439796 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1561273 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1528263 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1379659 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1476047 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1469605 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1432680 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1401188 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1502053 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1410585 (Python Code)

Max Activating Token Index: 806

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1573523 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1618693 (Python Code)

Max Activating Token Index: 162

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1464235 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1560809 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1538849 (Python Code)

Max Activating Token Index: 360

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1471491 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1626526 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1602260 (Python Code)

Max Activating Token Index: 229