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

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

Neuron 2595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3845. Min Act: -0.0003

Data Index: 285940 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3789. Min Act: -0.0003

Data Index: 806076 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3627. Min Act: -0.0003

Data Index: 530169 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3466. Min Act: -0.0002

Data Index: 724443 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3591. Min Act: -0.0002

Data Index: 1009621 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3458. Min Act: -0.0003

Data Index: 109835 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3584. Min Act: -0.0002

Data Index: 868180 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3393. Min Act: -0.0002

Data Index: 125205 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3339. Min Act: -0.0003

Data Index: 921801 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3408. Min Act: -0.0002

Data Index: 105535 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3281. Min Act: -0.0003

Data Index: 648738 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3284. Min Act: -0.0002

Data Index: 123492 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3128. Min Act: -0.0002

Data Index: 340996 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3603. Min Act: -0.0002

Data Index: 329067 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3277. Min Act: -0.0003

Data Index: 262677 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3290. Min Act: -0.0002

Data Index: 415247 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3160. Min Act: -0.0003

Data Index: 797431 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3133. Min Act: -0.0003

Data Index: 1285815 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.2996. Min Act: -0.0002

Data Index: 562736 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3002. Min Act: -0.0003

Data Index: 830060 (C4 (Web Text))

Max Activating Token Index: 259