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

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

Neuron 3331 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4384. Min Act: -0.0000

Data Index: 765173 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1130367 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3941. Min Act: -0.0000

Data Index: 158749 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1126902 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3783. Min Act: 0.0000

Data Index: 906352 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1048507 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3583. Min Act: -0.0000

Data Index: 289478 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3532. Min Act: -0.0000

Data Index: 125229 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3550. Min Act: -0.0000

Data Index: 215580 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3519. Min Act: -0.0000

Data Index: 41902 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1315137 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3556. Min Act: -0.0000

Data Index: 923111 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3423. Min Act: -0.0000

Data Index: 479149 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1211690 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3513. Min Act: -0.0000

Data Index: 182295 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3399. Min Act: -0.0000

Data Index: 125073 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3520. Min Act: -0.0000

Data Index: 185446 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3511. Min Act: -0.0000

Data Index: 294460 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3513. Min Act: -0.0000

Data Index: 729341 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4384. Min Range: -0.4384

Max Act: 0.3379. Min Act: -0.0000

Data Index: 28161 (C4 (Web Text))

Max Activating Token Index: 909