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

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

Neuron 4276 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: 2.3744. Min Range: -2.3744

Max Act: 2.3744. Min Act: -0.0000

Data Index: 369811 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.2748. Min Act: -0.0000

Data Index: 193526 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1005. Min Act: -0.0001

Data Index: 929562 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1869. Min Act: -0.0001

Data Index: 1193318 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.9965. Min Act: -0.0000

Data Index: 815090 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.0102. Min Act: -0.0000

Data Index: 1393 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1124. Min Act: -0.0000

Data Index: 798616 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.0865. Min Act: -0.0000

Data Index: 957898 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.9841. Min Act: -0.0000

Data Index: 558481 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.8492. Min Act: -0.0000

Data Index: 1487380 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1564. Min Act: -0.0000

Data Index: 1178016 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.0201. Min Act: -0.0000

Data Index: 969730 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1200. Min Act: -0.0000

Data Index: 361111 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.9959. Min Act: -0.0000

Data Index: 7002 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 2.3744. Min Range: -2.3744

Max Act: 2.1688. Min Act: -0.0000

Data Index: 1012798 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1475555 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.8529. Min Act: -0.0000

Data Index: 171491 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.7802. Min Act: -0.0000

Data Index: 1045918 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.9266. Min Act: -0.0000

Data Index: 758389 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 2.3744. Min Range: -2.3744

Max Act: 1.8051. Min Act: -0.0000

Data Index: 1093785 (C4 (Web Text))

Max Activating Token Index: 142