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

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

Neuron 2744 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: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1046474 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1858. Min Act: -0.0000

Data Index: 527065 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1040950 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1698. Min Act: -0.0000

Data Index: 296088 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1197576 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1533. Min Act: -0.0000

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1107727 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1676. Min Act: -0.0000

Data Index: 359314 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1551. Min Act: -0.0000

Data Index: 865299 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1437442 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1540. Min Act: -0.0000

Data Index: 579199 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1491. Min Act: -0.0000

Data Index: 264696 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1408. Min Act: 0.0000

Data Index: 1169865 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1017769 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1467. Min Act: -0.0000

Data Index: 45888 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1580173 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1337. Min Act: -0.0000

Data Index: 634379 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1053541 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1280. Min Act: -0.0000

Data Index: 352164 (C4 (Web Text))

Max Activating Token Index: 468