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

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

Neuron 3776 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3680. Min Act: -0.0001

Data Index: 555366 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2612. Min Act: -0.0001

Data Index: 168378 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1057862 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2804. Min Act: -0.0001

Data Index: 246926 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1309136 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1018597 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1320254 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2842. Min Act: -0.0001

Data Index: 220066 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2742. Min Act: -0.0001

Data Index: 1262752 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2630. Min Act: -0.0001

Data Index: 285671 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2643. Min Act: -0.0001

Data Index: 342453 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2848. Min Act: -0.0001

Data Index: 183430 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2522. Min Act: -0.0001

Data Index: 609392 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2677. Min Act: -0.0001

Data Index: 363143 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2501. Min Act: -0.0001

Data Index: 83243 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2548. Min Act: -0.0001

Data Index: 719270 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2629. Min Act: -0.0001

Data Index: 109209 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2426. Min Act: -0.0001

Data Index: 982846 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2564. Min Act: -0.0001

Data Index: 80369 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2753. Min Act: -0.0001

Data Index: 139055 (C4 (Web Text))

Max Activating Token Index: 814