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

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

Neuron 4474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6706. Min Act: -0.0001

Data Index: 1467961 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1551460 (Python Code)

Max Activating Token Index: 831

Text #2

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.6527. Min Act: -0.0001

Data Index: 1625673 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5532. Min Act: -0.0001

Data Index: 1651377 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5722. Min Act: -0.0001

Data Index: 1281189 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1616895 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5568. Min Act: -0.0001

Data Index: 1249302 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5619. Min Act: -0.0001

Data Index: 445162 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5385. Min Act: -0.0001

Data Index: 1573382 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1350695 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1643762 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5868. Min Act: -0.0001

Data Index: 818919 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5062. Min Act: -0.0001

Data Index: 1400377 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5617. Min Act: -0.0001

Data Index: 718180 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1646012 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5313. Min Act: -0.0001

Data Index: 1384162 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1426488 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1652328 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1635709 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.6706. Min Range: -0.6706

Max Act: 0.5023. Min Act: -0.0001

Data Index: 475585 (C4 (Web Text))

Max Activating Token Index: 360