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

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

Neuron 3279 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0639. Min Act: -0.0003

Data Index: 544733 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 360035 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0591. Min Act: -0.0003

Data Index: 519156 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0597. Min Act: -0.0003

Data Index: 215345 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0549. Min Act: -0.0003

Data Index: 386299 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0608. Min Act: -0.0003

Data Index: 576774 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0579. Min Act: -0.0003

Data Index: 795617 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1136602 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0588. Min Act: -0.0002

Data Index: 606369 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0543. Min Act: -0.0003

Data Index: 108048 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1530582 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0519. Min Act: -0.0002

Data Index: 815464 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1446541 (Python Code)

Max Activating Token Index: 257

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1020345 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0520. Min Act: -0.0002

Data Index: 526391 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1056744 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1452383 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0512. Min Act: -0.0003

Data Index: 412546 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0536. Min Act: -0.0002

Data Index: 328442 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0488. Min Act: -0.0003

Data Index: 349561 (C4 (Web Text))

Max Activating Token Index: 183