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

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

Neuron 5035 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1640995 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1528452 (Python Code)

Max Activating Token Index: 229

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1566187 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1534763 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1442756 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1483831 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1641959 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1364562 (Python Code)

Max Activating Token Index: 774

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1362810 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1541906 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1588290 (Python Code)

Max Activating Token Index: 904

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1520520 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1391671 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1367559 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1579336 (Python Code)

Max Activating Token Index: 282

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1408492 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1460872 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1653334 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1619717 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1527336 (Python Code)

Max Activating Token Index: 745