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

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

Neuron 4932 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: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1347508 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1262536 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0670. Min Act: -0.0002

Data Index: 303281 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0648. Min Act: -0.0002

Data Index: 994320 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0661. Min Act: -0.0002

Data Index: 413673 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0669. Min Act: -0.0002

Data Index: 595922 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1180441 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0677. Min Act: -0.0002

Data Index: 737068 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0592. Min Act: -0.0002

Data Index: 522357 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1053320 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0607. Min Act: -0.0002

Data Index: 108757 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0505. Min Act: -0.0002

Data Index: 79046 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0507. Min Act: -0.0002

Data Index: 263045 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0521. Min Act: -0.0002

Data Index: 898934 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0564. Min Act: -0.0002

Data Index: 831709 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0574. Min Act: -0.0002

Data Index: 748832 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0524. Min Act: -0.0002

Data Index: 352654 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0549. Min Act: -0.0002

Data Index: 219829 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1082904 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0471. Min Act: -0.0002

Data Index: 647270 (C4 (Web Text))

Max Activating Token Index: 215