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

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

Neuron 2606 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: 1.0843. Min Range: -1.0843

Max Act: 1.0843. Min Act: -0.0003

Data Index: 365871 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9828. Min Act: -0.0003

Data Index: 923762 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9633. Min Act: -0.0003

Data Index: 673578 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9205. Min Act: -0.0003

Data Index: 301055 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9339. Min Act: -0.0003

Data Index: 738844 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9124. Min Act: -0.0003

Data Index: 672651 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.0843. Min Range: -1.0843

Max Act: 1.0135. Min Act: -0.0003

Data Index: 712661 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9297. Min Act: -0.0003

Data Index: 1066735 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9452. Min Act: -0.0003

Data Index: 1050176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9099. Min Act: -0.0003

Data Index: 792750 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.8648. Min Act: -0.0003

Data Index: 296665 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9515. Min Act: -0.0003

Data Index: 1061683 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.8924. Min Act: -0.0003

Data Index: 113159 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.8691. Min Act: -0.0003

Data Index: 1214890 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.8578. Min Act: -0.0003

Data Index: 487034 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9559. Min Act: -0.0003

Data Index: 132594 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.7962. Min Act: -0.0003

Data Index: 1295075 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9326. Min Act: -0.0003

Data Index: 363420 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9555. Min Act: -0.0003

Data Index: 109786 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.8610. Min Act: -0.0003

Data Index: 1197066 (C4 (Web Text))

Max Activating Token Index: 866