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

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

Neuron 381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1297063 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1349747 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0504. Min Act: -0.0002

Data Index: 436337 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0001

Data Index: 138815 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1383568 (Python Code)

Max Activating Token Index: 150

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1379130 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1654543 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1577357 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1585584 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0368. Min Act: -0.0001

Data Index: 304725 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1441891 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1476515 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0382. Min Act: -0.0001

Data Index: 759261 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1534346 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1430856 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1288370 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1615983 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1632566 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1194997 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0330. Min Act: -0.0001

Data Index: 256926 (C4 (Web Text))

Max Activating Token Index: 393