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

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

Neuron 3500 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0562. Min Act: -0.0001

Data Index: 284009 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9210. Min Act: -0.0001

Data Index: 692058 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8430. Min Act: -0.0001

Data Index: 427946 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8376. Min Act: -0.0001

Data Index: 416915 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8944. Min Act: -0.0001

Data Index: 995197 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1180011 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8678. Min Act: -0.0001

Data Index: 1116699 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7836. Min Act: -0.0001

Data Index: 776675 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7913. Min Act: -0.0001

Data Index: 377853 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7058. Min Act: -0.0001

Data Index: 121329 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1178228 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7440. Min Act: -0.0001

Data Index: 841570 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8032. Min Act: -0.0001

Data Index: 528380 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7362. Min Act: -0.0001

Data Index: 334579 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7098. Min Act: -0.0001

Data Index: 688332 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1086434 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.6900. Min Act: -0.0001

Data Index: 950487 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1339619 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.6970. Min Act: -0.0001

Data Index: 748359 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.6570. Min Act: -0.0001

Data Index: 655486 (C4 (Web Text))

Max Activating Token Index: 34