Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1103 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0005

Data Index: 570779 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0589. Min Act: -0.0005

Data Index: 433082 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0590. Min Act: -0.0005

Data Index: 1286615 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0599. Min Act: -0.0005

Data Index: 1217182 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0596. Min Act: -0.0005

Data Index: 670753 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0609. Min Act: -0.0005

Data Index: 656277 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0607. Min Act: -0.0005

Data Index: 536701 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0605. Min Act: -0.0005

Data Index: 1014793 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0589. Min Act: -0.0005

Data Index: 415383 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0562. Min Act: -0.0005

Data Index: 617204 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0563. Min Act: -0.0005

Data Index: 197084 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0600. Min Act: -0.0005

Data Index: 6579 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0552. Min Act: -0.0005

Data Index: 815385 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0565. Min Act: -0.0005

Data Index: 100813 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0547. Min Act: -0.0005

Data Index: 901571 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0561. Min Act: -0.0005

Data Index: 82914 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0569. Min Act: -0.0005

Data Index: 1331689 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0562. Min Act: -0.0005

Data Index: 750370 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0555. Min Act: -0.0005

Data Index: 1246382 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0567. Min Act: -0.0005

Data Index: 1309593 (C4 (Web Text))

Max Activating Token Index: 948