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

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

Neuron 22 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1462541 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1426879 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1529664 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8578. Min Act: 0.0001

Data Index: 1577917 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7992. Min Act: 0.0001

Data Index: 1441637 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7646. Min Act: 0.0000

Data Index: 1542237 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1484116 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1410916 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1491589 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1378882 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1461609 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1619928 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1635850 (Python Code)

Max Activating Token Index: 460

Text #13

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1372229 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1469397 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1543544 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1535925 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1472610 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1370642 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1453948 (Python Code)

Max Activating Token Index: 389