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

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

Neuron 5655 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0702. Min Range: -1.0702

Max Act: 1.0525. Min Act: -0.0000

Data Index: 827615 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.0702. Min Range: -1.0702

Max Act: 1.0483. Min Act: -0.0000

Data Index: 355749 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.0702. Min Range: -1.0702

Max Act: 1.0009. Min Act: -0.0000

Data Index: 832526 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9874. Min Act: -0.0000

Data Index: 758010 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.0702. Min Range: -1.0702

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1281016 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9896. Min Act: -0.0000

Data Index: 92276 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9808. Min Act: -0.0000

Data Index: 565113 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1054691 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9503. Min Act: -0.0000

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9095. Min Act: -0.0000

Data Index: 901749 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9896. Min Act: -0.0000

Data Index: 351297 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9142. Min Act: -0.0000

Data Index: 180127 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1355104 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8531. Min Act: -0.0000

Data Index: 113677 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8739. Min Act: -0.0000

Data Index: 39921 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8829. Min Act: -0.0000

Data Index: 984304 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.9380. Min Act: -0.0000

Data Index: 747914 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8428. Min Act: -0.0000

Data Index: 599631 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8191. Min Act: -0.0000

Data Index: 440275 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.0702. Min Range: -1.0702

Max Act: 0.8422. Min Act: -0.0000

Data Index: 294801 (C4 (Web Text))

Max Activating Token Index: 488