Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3792 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0700. Min Range: -1.0700

Max Act: 1.0700. Min Act: -0.0000

Data Index: 327829 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.8843. Min Act: -0.0000

Data Index: 165264 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1266529 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.8259. Min Act: -0.0000

Data Index: 50824 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7736. Min Act: -0.0000

Data Index: 912519 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1357608 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7572. Min Act: -0.0000

Data Index: 484777 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7653. Min Act: -0.0000

Data Index: 982330 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7396. Min Act: -0.0000

Data Index: 317008 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7262. Min Act: -0.0000

Data Index: 903618 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7726. Min Act: -0.0000

Data Index: 208007 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7021. Min Act: -0.0000

Data Index: 401802 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1496106 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7471. Min Act: -0.0000

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1374828 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1287949 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7141. Min Act: -0.0000

Data Index: 553418 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.7441. Min Act: -0.0000

Data Index: 202465 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.6878. Min Act: -0.0000

Data Index: 42053 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.0700. Min Range: -1.0700

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1568122 (Python Code)

Max Activating Token Index: 43