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

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

Neuron 515 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1563362 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.9867. Min Act: -0.0000

Data Index: 1440844 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.4140. Min Act: 0.0000

Data Index: 1639977 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.2454. Min Act: -0.0000

Data Index: 1540753 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1566153 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1435576 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1393101 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.9299. Min Act: -0.0000

Data Index: 1410190 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 2.9867. Min Range: -2.9867

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1630869 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.7529. Min Act: -0.0000

Data Index: 1370871 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1395619 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.8064. Min Act: -0.0000

Data Index: 1382184 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1557238 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.6556. Min Act: -0.0000

Data Index: 1469382 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1361510 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1642128 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1405985 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1657021 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.3893. Min Act: -0.0000

Data Index: 1444714 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 2.9867. Min Range: -2.9867

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1422961 (Python Code)

Max Activating Token Index: 899