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

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

Neuron 3356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0550. Min Act: -0.0002

Data Index: 729264 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1356310 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1048558 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0538. Min Act: -0.0002

Data Index: 983053 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0518. Min Act: -0.0002

Data Index: 214888 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1031911 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0498. Min Act: -0.0002

Data Index: 622790 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0527. Min Act: -0.0002

Data Index: 693834 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0521. Min Act: -0.0002

Data Index: 153777 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0530. Min Act: -0.0002

Data Index: 999646 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1009661 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0556. Min Act: -0.0002

Data Index: 752843 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1007416 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0473. Min Act: -0.0002

Data Index: 6016 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0491. Min Act: -0.0002

Data Index: 600447 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0470. Min Act: -0.0002

Data Index: 673413 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0497. Min Act: -0.0002

Data Index: 766729 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1283022 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0484. Min Act: -0.0002

Data Index: 139726 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1215879 (C4 (Web Text))

Max Activating Token Index: 98