Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3173. Min Act: -0.0003

Data Index: 1276639 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3089. Min Act: -0.0003

Data Index: 382708 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3023. Min Act: -0.0004

Data Index: 864031 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.3100. Min Act: -0.0003

Data Index: 818541 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2976. Min Act: -0.0003

Data Index: 428939 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2899. Min Act: -0.0003

Data Index: 1022824 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2838. Min Act: -0.0004

Data Index: 1065233 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2824. Min Act: -0.0004

Data Index: 457352 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2885. Min Act: -0.0003

Data Index: 585642 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2882. Min Act: -0.0003

Data Index: 569602 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2803. Min Act: -0.0003

Data Index: 652667 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2620. Min Act: -0.0003

Data Index: 219899 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2783. Min Act: -0.0003

Data Index: 1295209 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2766. Min Act: -0.0003

Data Index: 851945 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2682. Min Act: -0.0003

Data Index: 433179 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2658. Min Act: -0.0004

Data Index: 613245 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2642. Min Act: -0.0004

Data Index: 426516 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2668. Min Act: -0.0003

Data Index: 258458 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2722. Min Act: -0.0003

Data Index: 809019 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.3173. Min Range: -0.3173

Max Act: 0.2633. Min Act: -0.0003

Data Index: 409757 (C4 (Web Text))

Max Activating Token Index: 152