Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1437853 (Python Code)

Max Activating Token Index: 490

Text #1

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1641521 (Python Code)

Max Activating Token Index: 842

Text #2

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1387447 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1462257 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1589118 (Python Code)

Max Activating Token Index: 908

Text #5

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1487984 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1656991 (Python Code)

Max Activating Token Index: 161

Text #7

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1617736 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1591611 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1551600 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1633285 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8467. Min Act: 0.0000

Data Index: 1430415 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1476893 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1424670 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1371905 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1578789 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1376380 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1657027 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1653434 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1492031 (Python Code)

Max Activating Token Index: 170