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

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

Neuron 2797 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1462964 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1054277 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1678. Min Act: -0.0001

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1402641 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1711. Min Act: -0.0001

Data Index: 577678 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1548. Min Act: -0.0001

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1586076 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1032037 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1395766 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1590984 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1514081 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1617. Min Act: -0.0001

Data Index: 341791 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1453465 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1499. Min Act: -0.0001

Data Index: 73146 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1565586 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1483. Min Act: -0.0001

Data Index: 573905 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1627894 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1493. Min Act: -0.0001

Data Index: 348831 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1378. Min Act: -0.0001

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1552. Min Act: -0.0001

Data Index: 796102 (C4 (Web Text))

Max Activating Token Index: 734