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

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

Neuron 1657 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: 0.5094. Min Range: -0.5094

Max Act: 0.5094. Min Act: -0.0002

Data Index: 1502402 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4047. Min Act: -0.0002

Data Index: 1489902 (Python Code)

Max Activating Token Index: 362

Text #2

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3447. Min Act: -0.0002

Data Index: 1556458 (Python Code)

Max Activating Token Index: 369

Text #3

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3432. Min Act: -0.0002

Data Index: 1515896 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3321. Min Act: -0.0002

Data Index: 1572561 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3206. Min Act: -0.0002

Data Index: 1372527 (Python Code)

Max Activating Token Index: 795

Text #6

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3250. Min Act: -0.0002

Data Index: 1534546 (Python Code)

Max Activating Token Index: 796

Text #7

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3250. Min Act: -0.0002

Data Index: 1470373 (Python Code)

Max Activating Token Index: 672

Text #8

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3263. Min Act: -0.0002

Data Index: 1530903 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3252. Min Act: -0.0002

Data Index: 1415962 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3068. Min Act: -0.0002

Data Index: 1438919 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3053. Min Act: -0.0002

Data Index: 1454002 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2886. Min Act: -0.0002

Data Index: 1409635 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3063. Min Act: -0.0002

Data Index: 1644029 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3065. Min Act: -0.0002

Data Index: 1464388 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3095. Min Act: -0.0002

Data Index: 1409578 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2788. Min Act: -0.0002

Data Index: 1601037 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2888. Min Act: -0.0002

Data Index: 1640903 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.2909. Min Act: -0.0002

Data Index: 1588822 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.3215. Min Act: -0.0002

Data Index: 1649759 (Python Code)

Max Activating Token Index: 764