Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6697. Min Act: -0.0001

Data Index: 43142 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6211. Min Act: -0.0001

Data Index: 841620 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1068689 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5816. Min Act: -0.0001

Data Index: 762800 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5884. Min Act: -0.0001

Data Index: 540391 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5828. Min Act: -0.0001

Data Index: 1040152 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5743. Min Act: -0.0001

Data Index: 580712 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5735. Min Act: -0.0001

Data Index: 1317484 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5714. Min Act: -0.0001

Data Index: 773825 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5453. Min Act: -0.0001

Data Index: 364215 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5447. Min Act: -0.0001

Data Index: 633017 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5285. Min Act: -0.0001

Data Index: 382796 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1286660 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5205. Min Act: -0.0001

Data Index: 1134075 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5345. Min Act: -0.0001

Data Index: 203612 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5361. Min Act: -0.0001

Data Index: 1149679 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5361. Min Act: -0.0001

Data Index: 363500 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5402. Min Act: -0.0001

Data Index: 930153 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5102. Min Act: -0.0001

Data Index: 200136 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5227. Min Act: -0.0001

Data Index: 843258 (C4 (Web Text))

Max Activating Token Index: 114