Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4512 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8622. Min Act: -0.0000

Data Index: 415978 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.8046. Min Act: -0.0000

Data Index: 912921 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7873. Min Act: -0.0000

Data Index: 819432 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7814. Min Act: -0.0000

Data Index: 326422 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7795. Min Act: -0.0000

Data Index: 56714 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1212876 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1314069 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7166. Min Act: -0.0000

Data Index: 230049 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7118. Min Act: -0.0000

Data Index: 843392 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1154913 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6276. Min Act: -0.0000

Data Index: 534664 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1297944 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.7066. Min Act: -0.0000

Data Index: 926365 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6781. Min Act: -0.0000

Data Index: 961248 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6354. Min Act: -0.0000

Data Index: 168564 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6337. Min Act: -0.0000

Data Index: 977506 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6340. Min Act: -0.0000

Data Index: 289612 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6221. Min Act: -0.0000

Data Index: 46011 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6187. Min Act: -0.0000

Data Index: 842175 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.8622. Min Range: -0.8622

Max Act: 0.6096. Min Act: -0.0000

Data Index: 125574 (C4 (Web Text))

Max Activating Token Index: 213