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

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

Neuron 4409 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.5211. Min Act: -0.0002

Data Index: 911901 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.6997. Min Act: -0.0002

Data Index: 1131215 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.7981. Min Act: -0.0002

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.5751. Min Act: -0.0002

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.2906. Min Act: -0.0002

Data Index: 279987 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.0132. Min Act: -0.0002

Data Index: 923494 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.3248. Min Act: -0.0002

Data Index: 649279 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.2189. Min Act: -0.0002

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.1566. Min Act: -0.0002

Data Index: 1238395 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.8517. Min Act: -0.0002

Data Index: 1307399 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 3.7981. Min Range: -3.7981

Max Act: 3.1643. Min Act: -0.0002

Data Index: 465910 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.7077. Min Act: -0.0002

Data Index: 1076591 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.9004. Min Act: -0.0002

Data Index: 1022375 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.9860. Min Act: -0.0002

Data Index: 655181 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.4531. Min Act: -0.0002

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.8809. Min Act: -0.0002

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.9761. Min Act: -0.0002

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.9516. Min Act: -0.0002

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.9447. Min Act: -0.0002

Data Index: 956701 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.7981. Min Range: -3.7981

Max Act: 2.6912. Min Act: -0.0002

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 191