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

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

Neuron 3562 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.9868. Min Act: -0.0000

Data Index: 1560843 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1565985 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1413500 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1224508 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1434773 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7254. Min Act: -0.0000

Data Index: 757242 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1093116 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1526754 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1383337 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1195214 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6914. Min Act: -0.0000

Data Index: 183683 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7349. Min Act: -0.0000

Data Index: 877015 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1457399 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1512168 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1472686 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1230302 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6358. Min Act: -0.0000

Data Index: 64455 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1414756 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1516825 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1621380 (Python Code)

Max Activating Token Index: 188