Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2135 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 473641 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1029869 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1286903 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0979. Min Act: -0.0001

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1378359 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0998. Min Act: -0.0002

Data Index: 369240 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0918. Min Act: -0.0002

Data Index: 587998 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0861. Min Act: -0.0002

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0813. Min Act: -0.0001

Data Index: 487786 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0902. Min Act: -0.0001

Data Index: 841490 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0886. Min Act: -0.0001

Data Index: 932434 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1171992 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0809. Min Act: -0.0002

Data Index: 32678 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1117262 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0745. Min Act: -0.0001

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1125670 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1200459 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1615765 (Python Code)

Max Activating Token Index: 961

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0785. Min Act: -0.0002

Data Index: 588183 (C4 (Web Text))

Max Activating Token Index: 990