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

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

Neuron 4728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1603580 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0566. Min Act: -0.0000

Data Index: 364676 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1554048 (Python Code)

Max Activating Token Index: 914

Text #3

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1143956 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1287994 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0538. Min Act: -0.0000

Data Index: 598991 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1532150 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1487969 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0528. Min Act: -0.0000

Data Index: 738940 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1204578 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0473. Min Act: -0.0000

Data Index: 559363 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1060475 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0447. Min Act: -0.0000

Data Index: 525092 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1511875 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1440559 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1112667 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0486. Min Act: -0.0000

Data Index: 242786 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1597521 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1380756 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0432. Min Act: -0.0000

Data Index: 883843 (C4 (Web Text))

Max Activating Token Index: 336