Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 242 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 996015 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1421708 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1075885 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1557620 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0875. Min Act: -0.0002

Data Index: 713703 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1482384 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1530252 (Python Code)

Max Activating Token Index: 284

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1365419 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1084223 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1509434 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1556390 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0859. Min Act: -0.0002

Data Index: 509460 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1378697 (Python Code)

Max Activating Token Index: 685

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1411210 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1496026 (Python Code)

Max Activating Token Index: 1001

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1505055 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0821. Min Act: -0.0002

Data Index: 520795 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1538157 (Python Code)

Max Activating Token Index: 395

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1367471 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1604033 (Python Code)

Max Activating Token Index: 352