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

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

Neuron 2804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0000

Data Index: 771104 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1195298 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1022253 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1603. Min Act: -0.0001

Data Index: 953611 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1071671 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1325816 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1626. Min Act: -0.0000

Data Index: 135627 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1551. Min Act: -0.0000

Data Index: 574689 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1021692 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1251550 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1571. Min Act: -0.0001

Data Index: 264671 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1511. Min Act: 0.0001

Data Index: 855598 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1483. Min Act: -0.0001

Data Index: 844315 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1052825 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1471. Min Act: -0.0000

Data Index: 572844 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1454. Min Act: -0.0000

Data Index: 488957 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1021816 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1276313 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1449. Min Act: -0.0000

Data Index: 941639 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1409. Min Act: -0.0000

Data Index: 340069 (C4 (Web Text))

Max Activating Token Index: 635