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

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

Neuron 5938 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.5473. Min Act: -0.0000

Data Index: 479469 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.2417. Min Act: -0.0000

Data Index: 689127 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.1650. Min Act: -0.0000

Data Index: 484390 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.3462. Min Act: -0.0000

Data Index: 254495 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.2651. Min Act: -0.0000

Data Index: 1356944 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.2446. Min Act: -0.0000

Data Index: 784360 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.1076. Min Act: -0.0000

Data Index: 517061 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.1755. Min Act: -0.0000

Data Index: 699767 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.1404. Min Act: -0.0000

Data Index: 102963 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.0349. Min Act: -0.0000

Data Index: 1185004 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.8932. Min Act: -0.0000

Data Index: 729426 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.1252. Min Act: -0.0000

Data Index: 180385 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.8156. Min Act: -0.0000

Data Index: 150094 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.9113. Min Act: -0.0000

Data Index: 60857 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1406050 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.6411. Min Act: -0.0000

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 2.5473. Min Range: -2.5473

Max Act: 2.0021. Min Act: -0.0000

Data Index: 409801 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.7002. Min Act: -0.0000

Data Index: 1597395 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1630446 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.5473. Min Range: -2.5473

Max Act: 1.6551. Min Act: -0.0000

Data Index: 215994 (C4 (Web Text))

Max Activating Token Index: 51