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

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

Neuron 1430 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1644. Min Range: -4.1644

Max Act: 4.1644. Min Act: -0.0000

Data Index: 1379318 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.8214. Min Act: -0.0000

Data Index: 1408012 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 4.1644. Min Range: -4.1644

Max Act: 4.0882. Min Act: -0.0000

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 4.1644. Min Range: -4.1644

Max Act: 4.0605. Min Act: -0.0000

Data Index: 1539232 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.9342. Min Act: -0.0000

Data Index: 863594 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.9541. Min Act: -0.0000

Data Index: 736331 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.7708. Min Act: -0.0000

Data Index: 969613 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.9234. Min Act: -0.0000

Data Index: 19403 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.9295. Min Act: -0.0000

Data Index: 280474 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.5761. Min Act: -0.0000

Data Index: 1027591 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.9122. Min Act: -0.0000

Data Index: 453616 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.7366. Min Act: -0.0000

Data Index: 1071838 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.8990. Min Act: -0.0000

Data Index: 1232629 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.8895. Min Act: -0.0000

Data Index: 795099 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.8839. Min Act: -0.0000

Data Index: 617999 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.7181. Min Act: -0.0000

Data Index: 1463892 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.6917. Min Act: -0.0000

Data Index: 1609416 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.8214. Min Act: -0.0000

Data Index: 1450293 (Python Code)

Max Activating Token Index: 739

Text #18

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.6298. Min Act: -0.0000

Data Index: 251069 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 4.1644. Min Range: -4.1644

Max Act: 3.7878. Min Act: -0.0000

Data Index: 91859 (C4 (Web Text))

Max Activating Token Index: 468