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

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

Neuron 926 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.9691. Min Act: -0.0002

Data Index: 1167934 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8923. Min Act: -0.0002

Data Index: 1641356 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8908. Min Act: -0.0002

Data Index: 1415730 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8014. Min Act: -0.0002

Data Index: 1419689 (Python Code)

Max Activating Token Index: 682

Text #4

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.7029. Min Act: -0.0002

Data Index: 1630619 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.6011. Min Act: -0.0002

Data Index: 1383430 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.6731. Min Act: -0.0002

Data Index: 1555702 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.5397. Min Act: -0.0002

Data Index: 1412286 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.5020. Min Act: -0.0002

Data Index: 1564962 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.5096. Min Act: -0.0002

Data Index: 1397332 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.3374. Min Act: -0.0002

Data Index: 1621068 (Python Code)

Max Activating Token Index: 761

Text #11

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.3033. Min Act: -0.0002

Data Index: 252 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.3061. Min Act: -0.0002

Data Index: 1397684 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2888. Min Act: -0.0002

Data Index: 836365 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.3049. Min Act: -0.0002

Data Index: 1382527 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2673. Min Act: -0.0002

Data Index: 464344 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2309. Min Act: -0.0002

Data Index: 901413 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2283. Min Act: -0.0002

Data Index: 1339948 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2498. Min Act: -0.0002

Data Index: 844180 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.2088. Min Act: -0.0002

Data Index: 1644423 (Python Code)

Max Activating Token Index: 849