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

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

Neuron 1287 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0618. Min Act: -0.0001

Data Index: 50758 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0131. Min Act: -0.0001

Data Index: 710182 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.0794. Min Range: -1.0794

Max Act: 1.0794. Min Act: -0.0001

Data Index: 1281483 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9362. Min Act: -0.0001

Data Index: 517266 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1350492 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8356. Min Act: -0.0001

Data Index: 831458 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8015. Min Act: -0.0001

Data Index: 610247 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8122. Min Act: -0.0001

Data Index: 228497 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.5571. Min Act: -0.0001

Data Index: 458242 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7727. Min Act: -0.0001

Data Index: 435209 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7599. Min Act: -0.0001

Data Index: 698505 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.8357. Min Act: -0.0001

Data Index: 105975 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6622. Min Act: -0.0001

Data Index: 889378 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7696. Min Act: -0.0001

Data Index: 283548 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6869. Min Act: -0.0001

Data Index: 875060 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6473. Min Act: -0.0001

Data Index: 462919 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7975. Min Act: -0.0001

Data Index: 404656 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7551. Min Act: -0.0001

Data Index: 85102 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.6939. Min Act: -0.0001

Data Index: 152042 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.0794. Min Range: -1.0794

Max Act: 0.7557. Min Act: -0.0001

Data Index: 545395 (C4 (Web Text))

Max Activating Token Index: 201