Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0003

Data Index: 237903 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1043. Min Act: -0.0003

Data Index: 577424 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1003. Min Act: -0.0003

Data Index: 402899 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1001. Min Act: -0.0003

Data Index: 90157 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0988. Min Act: -0.0003

Data Index: 17738 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1259974 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0903. Min Act: -0.0003

Data Index: 220178 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0897. Min Act: -0.0003

Data Index: 410786 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1067953 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1282797 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0860. Min Act: -0.0003

Data Index: 737798 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1182982 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0844. Min Act: -0.0003

Data Index: 223771 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0888. Min Act: -0.0003

Data Index: 392635 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1261072 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0855. Min Act: -0.0003

Data Index: 206865 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0810. Min Act: -0.0003

Data Index: 240746 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0840. Min Act: -0.0003

Data Index: 706469 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0867. Min Act: -0.0003

Data Index: 32315 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0856. Min Act: -0.0003

Data Index: 803414 (C4 (Web Text))

Max Activating Token Index: 353