Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6077 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0000

Data Index: 275233 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3243. Min Act: -0.0000

Data Index: 185024 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1081519 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3401. Min Act: -0.0000

Data Index: 383986 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1182418 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3149. Min Act: -0.0000

Data Index: 203274 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2854. Min Act: -0.0000

Data Index: 492606 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2897. Min Act: -0.0000

Data Index: 663570 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2824. Min Act: -0.0000

Data Index: 868488 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2827. Min Act: -0.0000

Data Index: 478154 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2879. Min Act: -0.0000

Data Index: 987825 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1055034 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2719. Min Act: 0.0000

Data Index: 692714 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2589. Min Act: -0.0000

Data Index: 922997 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2657. Min Act: 0.0000

Data Index: 320235 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2624. Min Act: -0.0000

Data Index: 657704 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2619. Min Act: -0.0000

Data Index: 742242 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2654. Min Act: 0.0000

Data Index: 1004005 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1035544 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2519. Min Act: -0.0000

Data Index: 997551 (C4 (Web Text))

Max Activating Token Index: 115