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

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

Neuron 3435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3202. Min Act: -0.0000

Data Index: 815990 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1260310 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3078. Min Act: -0.0000

Data Index: 846211 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3197. Min Act: -0.0000

Data Index: 714802 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1042646 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2899. Min Act: -0.0000

Data Index: 870793 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2971. Min Act: -0.0000

Data Index: 944550 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1162667 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2901. Min Act: -0.0000

Data Index: 536282 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2975. Min Act: -0.0000

Data Index: 171696 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1066683 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2961. Min Act: -0.0000

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2802. Min Act: -0.0000

Data Index: 500994 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2809. Min Act: -0.0000

Data Index: 261746 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1003744 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2994. Min Act: -0.0000

Data Index: 240895 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2667. Min Act: -0.0000

Data Index: 659526 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1118640 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2848. Min Act: -0.0000

Data Index: 935703 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1206711 (C4 (Web Text))

Max Activating Token Index: 607