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

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

Neuron 700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0002

Data Index: 370809 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0501. Min Act: -0.0002

Data Index: 392298 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0498. Min Act: -0.0002

Data Index: 592411 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1253232 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0417. Min Act: -0.0002

Data Index: 228875 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1124048 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1335120 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1047243 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0405. Min Act: -0.0002

Data Index: 47277 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0407. Min Act: -0.0002

Data Index: 194086 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0393. Min Act: -0.0002

Data Index: 347548 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0404. Min Act: -0.0002

Data Index: 189800 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0375. Min Act: -0.0002

Data Index: 905714 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0415. Min Act: -0.0002

Data Index: 418662 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0378. Min Act: -0.0002

Data Index: 460881 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0388. Min Act: -0.0002

Data Index: 569744 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1245113 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0382. Min Act: -0.0002

Data Index: 305740 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0363. Min Act: -0.0002

Data Index: 676871 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0376. Min Act: -0.0002

Data Index: 87677 (C4 (Web Text))

Max Activating Token Index: 565