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

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

Neuron 3824 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: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0002

Data Index: 367946 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1376075 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0910. Min Act: -0.0002

Data Index: 704145 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0904. Min Act: -0.0002

Data Index: 248108 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0900. Min Act: -0.0002

Data Index: 241174 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1152040 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0822. Min Act: -0.0002

Data Index: 478007 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1341088 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1100486 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0851. Min Act: -0.0002

Data Index: 541304 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0842. Min Act: -0.0002

Data Index: 47253 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1435818 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0761. Min Act: -0.0002

Data Index: 828617 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1133807 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0694. Min Act: -0.0002

Data Index: 958930 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1557572 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0698. Min Act: -0.0002

Data Index: 749576 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0760. Min Act: -0.0002

Data Index: 452642 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1246588 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0685. Min Act: -0.0002

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 293