Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9628. Min Act: -0.0000

Data Index: 1483337 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.0818. Min Act: -0.0000

Data Index: 1598547 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.8600. Min Act: -0.0000

Data Index: 1461773 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.0142. Min Act: -0.0000

Data Index: 1636795 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.8180. Min Act: -0.0000

Data Index: 1427286 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.7551. Min Act: -0.0000

Data Index: 1486497 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9412. Min Act: -0.0000

Data Index: 1486785 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.0661. Min Act: -0.0000

Data Index: 1618760 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9882. Min Act: -0.0000

Data Index: 1473317 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.0486. Min Act: -0.0000

Data Index: 1375074 (Python Code)

Max Activating Token Index: 825

Text #10

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.2125. Min Act: -0.0000

Data Index: 1647638 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.8572. Min Act: -0.0000

Data Index: 1654613 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.8666. Min Act: -0.0000

Data Index: 1489073 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9532. Min Act: -0.0000

Data Index: 1433637 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 4.2125. Min Range: -4.2125

Max Act: 4.1374. Min Act: -0.0000

Data Index: 1510934 (Python Code)

Max Activating Token Index: 721

Text #15

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.6732. Min Act: -0.0000

Data Index: 1466683 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9336. Min Act: -0.0000

Data Index: 1398280 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.7817. Min Act: -0.0000

Data Index: 1588968 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.7991. Min Act: -0.0000

Data Index: 1492924 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 4.2125. Min Range: -4.2125

Max Act: 3.9201. Min Act: -0.0000

Data Index: 1370610 (Python Code)

Max Activating Token Index: 551