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

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

Neuron 1080 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: 5.0078. Min Range: -5.0078

Max Act: 5.0078. Min Act: -0.0000

Data Index: 1469237 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 5.0078. Min Range: -5.0078

Max Act: 4.7043. Min Act: -0.0000

Data Index: 1506382 (Python Code)

Max Activating Token Index: 766

Text #2

Max Range: 5.0078. Min Range: -5.0078

Max Act: 4.1189. Min Act: -0.0000

Data Index: 1570866 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1604661 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.4283. Min Act: -0.0000

Data Index: 1473332 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.1020. Min Act: -0.0000

Data Index: 1331856 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.5198. Min Act: -0.0000

Data Index: 1585606 (Python Code)

Max Activating Token Index: 915

Text #7

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.2871. Min Act: -0.0000

Data Index: 1415203 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1607866 (Python Code)

Max Activating Token Index: 984

Text #9

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.7154. Min Act: -0.0000

Data Index: 1504812 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.1920. Min Act: -0.0000

Data Index: 1509441 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.9899. Min Act: -0.0000

Data Index: 1605291 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.2814. Min Act: -0.0000

Data Index: 1436528 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.9126. Min Act: -0.0000

Data Index: 1483110 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.9006. Min Act: -0.0000

Data Index: 1386319 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.8603. Min Act: -0.0000

Data Index: 1491982 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 5.0078. Min Range: -5.0078

Max Act: 3.1255. Min Act: -0.0000

Data Index: 1471617 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.7092. Min Act: -0.0000

Data Index: 860516 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.6503. Min Act: -0.0000

Data Index: 1397906 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 5.0078. Min Range: -5.0078

Max Act: 2.5209. Min Act: -0.0000

Data Index: 1636629 (Python Code)

Max Activating Token Index: 966