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

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

Neuron 3354 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1480. Min Range: -8.1480

Max Act: 8.1480. Min Act: -0.0000

Data Index: 1642580 (Python Code)

Max Activating Token Index: 551

Text #1

Max Range: 8.1480. Min Range: -8.1480

Max Act: 7.6135. Min Act: -0.0000

Data Index: 1380595 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.8334. Min Act: -0.0000

Data Index: 1480635 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 8.1480. Min Range: -8.1480

Max Act: 7.2713. Min Act: -0.0000

Data Index: 1616034 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 8.1480. Min Range: -8.1480

Max Act: 7.3613. Min Act: -0.0000

Data Index: 1620336 (Python Code)

Max Activating Token Index: 791

Text #5

Max Range: 8.1480. Min Range: -8.1480

Max Act: 7.0909. Min Act: -0.0000

Data Index: 1374309 (Python Code)

Max Activating Token Index: 464

Text #6

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.7830. Min Act: -0.0000

Data Index: 1521304 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.3642. Min Act: -0.0000

Data Index: 1414197 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.9082. Min Act: -0.0000

Data Index: 1523441 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.3889. Min Act: -0.0000

Data Index: 1651058 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.7558. Min Act: -0.0000

Data Index: 1486781 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.5671. Min Act: -0.0000

Data Index: 1425534 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.9465. Min Act: -0.0000

Data Index: 1360560 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.5458. Min Act: -0.0000

Data Index: 1504692 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.2918. Min Act: -0.0000

Data Index: 1489241 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.4891. Min Act: -0.0000

Data Index: 1415088 (Python Code)

Max Activating Token Index: 183

Text #16

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.2779. Min Act: -0.0000

Data Index: 1493563 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.4678. Min Act: -0.0000

Data Index: 1379371 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.4489. Min Act: -0.0000

Data Index: 1508606 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 8.1480. Min Range: -8.1480

Max Act: 6.4457. Min Act: -0.0000

Data Index: 1487722 (Python Code)

Max Activating Token Index: 614