Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1646. Min Act: -0.0000

Data Index: 419919 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1073916 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1583989 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1133052 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1297301 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1534533 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1054477 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1623. Min Act: -0.0001

Data Index: 297040 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1782. Min Act: -0.0000

Data Index: 712247 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1559. Min Act: -0.0001

Data Index: 739025 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1011831 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1637. Min Act: -0.0000

Data Index: 864576 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1332. Min Act: -0.0000

Data Index: 641615 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1393810 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1458. Min Act: -0.0001

Data Index: 724427 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1603715 (Python Code)

Max Activating Token Index: 655

Text #16

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1143182 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1433810 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1574562 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1419. Min Act: -0.0001

Data Index: 233728 (C4 (Web Text))

Max Activating Token Index: 814