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

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

Neuron 3922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6800. Min Range: -2.6800

Max Act: 2.6800. Min Act: -0.0000

Data Index: 1377556 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1548379 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1439994 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1591973 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.6242. Min Act: -0.0000

Data Index: 302502 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1379162 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1394824 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1535002 (Python Code)

Max Activating Token Index: 1021

Text #8

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.5323. Min Act: -0.0000

Data Index: 1555688 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1508781 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1516439 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1621951 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1399877 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.4967. Min Act: -0.0000

Data Index: 1519122 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1146642 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1543608 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1452227 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1405224 (Python Code)

Max Activating Token Index: 782

Text #18

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1595833 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 2.6800. Min Range: -2.6800

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1637562 (Python Code)

Max Activating Token Index: 345