Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 880 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1656697 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1570697 (Python Code)

Max Activating Token Index: 836

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1405495 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1442471 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1450406 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1611002 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1538942 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1574494 (Python Code)

Max Activating Token Index: 115

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1473156 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1388546 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1504397 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1441524 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1045119 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1583181 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1437915 (Python Code)

Max Activating Token Index: 1021

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1434315 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1523768 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1649144 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1613270 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1552074 (Python Code)

Max Activating Token Index: 750