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

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

Neuron 4777 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0000

Data Index: 411803 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0623. Min Act: -0.0000

Data Index: 343687 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0549. Min Act: -0.0000

Data Index: 952190 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0557. Min Act: -0.0000

Data Index: 527085 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0496. Min Act: -0.0000

Data Index: 843756 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0528. Min Act: -0.0000

Data Index: 934136 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0529. Min Act: -0.0000

Data Index: 299449 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0503. Min Act: 0.0000

Data Index: 198177 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0538. Min Act: -0.0000

Data Index: 930996 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0519. Min Act: -0.0000

Data Index: 680414 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1341770 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0494. Min Act: -0.0000

Data Index: 472999 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0477. Min Act: -0.0000

Data Index: 575469 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0487. Min Act: -0.0000

Data Index: 322365 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0510. Min Act: -0.0000

Data Index: 840754 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0488. Min Act: -0.0000

Data Index: 731695 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1383939 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0471. Min Act: -0.0000

Data Index: 407127 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0457. Min Act: -0.0000

Data Index: 501001 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1363342 (Python Code)

Max Activating Token Index: 918