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

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

Neuron 4947 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: 2.5587. Min Range: -2.5587

Max Act: 2.5587. Min Act: -0.0000

Data Index: 1628901 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.1260. Min Act: -0.0000

Data Index: 1413250 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1492325 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1557416 (Python Code)

Max Activating Token Index: 668

Text #4

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1396521 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.1413. Min Act: -0.0000

Data Index: 1422791 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9729. Min Act: -0.0000

Data Index: 1613504 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9228. Min Act: -0.0000

Data Index: 1620567 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1539436 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 2.5587. Min Range: -2.5587

Max Act: 2.1068. Min Act: -0.0000

Data Index: 1491386 (Python Code)

Max Activating Token Index: 997

Text #10

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9037. Min Act: -0.0000

Data Index: 1411710 (Python Code)

Max Activating Token Index: 546

Text #11

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9276. Min Act: -0.0000

Data Index: 1461043 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1593544 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9458. Min Act: -0.0000

Data Index: 1374285 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.9399. Min Act: -0.0000

Data Index: 1441678 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1510041 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1382534 (Python Code)

Max Activating Token Index: 289

Text #17

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8700. Min Act: -0.0000

Data Index: 1636317 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1531787 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 2.5587. Min Range: -2.5587

Max Act: 1.8506. Min Act: -0.0000

Data Index: 1589829 (Python Code)

Max Activating Token Index: 174