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

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

Neuron 4962 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.9329. Min Act: -0.0000

Data Index: 324694 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1077241 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.9590. Min Act: -0.0000

Data Index: 206979 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1182357 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8683. Min Act: -0.0000

Data Index: 475235 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.9312. Min Act: -0.0000

Data Index: 743677 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8732. Min Act: -0.0000

Data Index: 23718 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8525. Min Act: -0.0000

Data Index: 199107 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8275. Min Act: -0.0000

Data Index: 287267 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8409. Min Act: -0.0000

Data Index: 323616 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7929. Min Act: -0.0000

Data Index: 998728 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.8261. Min Act: -0.0000

Data Index: 63168 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1307568 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7924. Min Act: -0.0000

Data Index: 889247 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7467. Min Act: -0.0000

Data Index: 744830 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7830. Min Act: -0.0000

Data Index: 771279 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7555. Min Act: -0.0001

Data Index: 943190 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1055383 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.6989. Min Act: -0.0000

Data Index: 258751 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.9590. Min Range: -0.9590

Max Act: 0.7209. Min Act: -0.0000

Data Index: 15461 (C4 (Web Text))

Max Activating Token Index: 448