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

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

Neuron 3854 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1620971 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1495884 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1374843 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1546621 (Python Code)

Max Activating Token Index: 420

Text #4

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1491556 (Python Code)

Max Activating Token Index: 387

Text #5

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1375569 (Python Code)

Max Activating Token Index: 272

Text #6

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1545169 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1615477 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1453038 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1655895 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1645843 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1515530 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1414671 (Python Code)

Max Activating Token Index: 697

Text #13

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1450643 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1428545 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1364981 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1552936 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1635043 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1504619 (Python Code)

Max Activating Token Index: 409

Text #19

Max Range: 0.9772. Min Range: -0.9772

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1459006 (Python Code)

Max Activating Token Index: 995