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

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

Neuron 4196 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1491330 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1514435 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1380279 (Python Code)

Max Activating Token Index: 676

Text #3

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1492602 (Python Code)

Max Activating Token Index: 519

Text #4

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1549229 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1433363 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1409452 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3714. Min Act: 0.0000

Data Index: 1503258 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3679. Min Act: 0.0000

Data Index: 1445894 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1587003 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1417676 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3716. Min Act: -0.0000

Data Index: 905638 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1633034 (Python Code)

Max Activating Token Index: 452

Text #13

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1534906 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1523291 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3457. Min Act: -0.0000

Data Index: 850500 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1612441 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1495557 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1600530 (Python Code)

Max Activating Token Index: 218

Text #19

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1362590 (Python Code)

Max Activating Token Index: 296