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

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

Neuron 677 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0398. Min Act: -0.0001

Data Index: 22924 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0384. Min Act: -0.0001

Data Index: 419497 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1167536 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1322690 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0375. Min Act: -0.0001

Data Index: 772574 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1270177 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1094949 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0001

Data Index: 585136 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0363. Min Act: -0.0001

Data Index: 969313 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0374. Min Act: -0.0001

Data Index: 528453 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0358. Min Act: -0.0001

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0363. Min Act: -0.0001

Data Index: 991815 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0349. Min Act: -0.0001

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0348. Min Act: -0.0001

Data Index: 146744 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1187916 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0327. Min Act: -0.0001

Data Index: 987641 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1502173 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0321. Min Act: -0.0001

Data Index: 330433 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0336. Min Act: -0.0001

Data Index: 296645 (C4 (Web Text))

Max Activating Token Index: 69