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

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

Neuron 3574 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1130032 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.6022. Min Act: -0.0000

Data Index: 638889 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1114514 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5901. Min Act: -0.0000

Data Index: 685620 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5489. Min Act: -0.0000

Data Index: 641073 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5439. Min Act: -0.0000

Data Index: 132719 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5458. Min Act: -0.0000

Data Index: 134604 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5526. Min Act: -0.0000

Data Index: 874534 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5309. Min Act: -0.0000

Data Index: 8682 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5403. Min Act: -0.0000

Data Index: 371238 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5317. Min Act: -0.0000

Data Index: 108178 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5528. Min Act: -0.0000

Data Index: 668083 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5440. Min Act: -0.0000

Data Index: 248726 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1108747 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5406. Min Act: -0.0000

Data Index: 353988 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.4568. Min Act: -0.0000

Data Index: 731441 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5284. Min Act: -0.0000

Data Index: 6889 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.4968. Min Act: -0.0000

Data Index: 485877 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.4881. Min Act: -0.0000

Data Index: 167731 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.6022. Min Range: -0.6022

Max Act: 0.5218. Min Act: -0.0000

Data Index: 911171 (C4 (Web Text))

Max Activating Token Index: 319