Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0002

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0363. Min Act: -0.0002

Data Index: 808570 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0349. Min Act: -0.0002

Data Index: 987674 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1609181 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1586170 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0315. Min Act: -0.0002

Data Index: 546744 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0323. Min Act: -0.0002

Data Index: 635233 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0327. Min Act: -0.0002

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0320. Min Act: -0.0002

Data Index: 484733 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1643377 (Python Code)

Max Activating Token Index: 954

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0329. Min Act: -0.0002

Data Index: 605005 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0304. Min Act: -0.0002

Data Index: 711198 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0301. Min Act: -0.0002

Data Index: 251079 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0294. Min Act: -0.0002

Data Index: 703467 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0290. Min Act: -0.0002

Data Index: 311768 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0290. Min Act: -0.0002

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1616594 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1447662 (Python Code)

Max Activating Token Index: 573

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0291. Min Act: -0.0001

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0283. Min Act: -0.0002

Data Index: 643489 (C4 (Web Text))

Max Activating Token Index: 665