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

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

Neuron 1342 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1432896 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1509846 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1456655 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1560337 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1621346 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1539712 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1646925 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1567988 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1374873 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1395740 (Python Code)

Max Activating Token Index: 746

Text #10

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1390525 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1403201 (Python Code)

Max Activating Token Index: 727

Text #12

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1637407 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1531741 (Python Code)

Max Activating Token Index: 872

Text #14

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1562271 (Python Code)

Max Activating Token Index: 642

Text #15

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1417966 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1630931 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1599483 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1506841 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.1966. Min Range: -0.1966

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1562559 (Python Code)

Max Activating Token Index: 783