Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0564. Min Act: -0.0005

Data Index: 973600 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0541. Min Act: -0.0005

Data Index: 805506 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0528. Min Act: -0.0005

Data Index: 475053 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0513. Min Act: -0.0004

Data Index: 1036309 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0497. Min Act: -0.0005

Data Index: 983712 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0482. Min Act: -0.0005

Data Index: 809854 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0511. Min Act: -0.0005

Data Index: 1338444 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0488. Min Act: -0.0005

Data Index: 258966 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0498. Min Act: -0.0005

Data Index: 690265 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0506. Min Act: -0.0005

Data Index: 760556 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0527. Min Act: -0.0005

Data Index: 1247915 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0513. Min Act: -0.0005

Data Index: 966240 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0498. Min Act: -0.0005

Data Index: 679724 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0509. Min Act: -0.0005

Data Index: 140630 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0466. Min Act: -0.0005

Data Index: 506390 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0499. Min Act: -0.0004

Data Index: 114332 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0512. Min Act: -0.0005

Data Index: 797985 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0502. Min Act: -0.0005

Data Index: 243437 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0496. Min Act: -0.0005

Data Index: 875674 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0564. Min Range: -0.0564

Max Act: 0.0514. Min Act: -0.0004

Data Index: 532889 (C4 (Web Text))

Max Activating Token Index: 99