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

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

Neuron 959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2838. Min Act: -0.0000

Data Index: 249157 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2700. Min Act: -0.0000

Data Index: 740035 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2524. Min Act: -0.0000

Data Index: 168209 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2345. Min Act: -0.0000

Data Index: 758654 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2128. Min Act: -0.0000

Data Index: 508160 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1177823 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1914. Min Act: -0.0000

Data Index: 481822 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1851. Min Act: -0.0000

Data Index: 443983 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1172300 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1901. Min Act: -0.0000

Data Index: 611677 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1008570 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1833. Min Act: -0.0000

Data Index: 819085 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1651. Min Act: -0.0000

Data Index: 429904 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1622. Min Act: -0.0000

Data Index: 770535 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1080058 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1333554 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1672. Min Act: -0.0000

Data Index: 583593 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1085463 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1788. Min Act: -0.0000

Data Index: 228874 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1514. Min Act: -0.0000

Data Index: 117267 (C4 (Web Text))

Max Activating Token Index: 320