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

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

Neuron 3650 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: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1637065 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1231524 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0368. Min Act: -0.0001

Data Index: 432387 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1507450 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1439202 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0345. Min Act: -0.0001

Data Index: 95059 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0365. Min Act: -0.0001

Data Index: 2075 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0314. Min Act: -0.0001

Data Index: 484164 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1580412 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1398869 (Python Code)

Max Activating Token Index: 693

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1370479 (Python Code)

Max Activating Token Index: 867

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1644602 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1474623 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1501201 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0317. Min Act: -0.0001

Data Index: 289578 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0001

Data Index: 327353 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1414267 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1375165 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1598127 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1625235 (Python Code)

Max Activating Token Index: 962