Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0882. Min Act: -0.0001

Data Index: 596983 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0786. Min Act: -0.0001

Data Index: 775519 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0763. Min Act: -0.0001

Data Index: 315476 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0742. Min Act: -0.0001

Data Index: 885071 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0731. Min Act: -0.0001

Data Index: 9715 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0609. Min Act: -0.0001

Data Index: 898100 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0599. Min Act: -0.0001

Data Index: 251054 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1303697 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0579. Min Act: -0.0001

Data Index: 951106 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0563. Min Act: -0.0001

Data Index: 592718 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0557. Min Act: -0.0001

Data Index: 133115 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1346290 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0479. Min Act: -0.0001

Data Index: 201662 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0516. Min Act: -0.0001

Data Index: 38212 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1023531 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0520. Min Act: -0.0001

Data Index: 288745 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0484. Min Act: -0.0001

Data Index: 241108 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1113362 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0567. Min Act: -0.0001

Data Index: 523671 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0505. Min Act: -0.0001

Data Index: 885424 (C4 (Web Text))

Max Activating Token Index: 386