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

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

Neuron 4788 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1455. Min Act: -0.0001

Data Index: 185105 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1205052 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1077. Min Act: -0.0001

Data Index: 956734 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0953. Min Act: -0.0001

Data Index: 135199 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1185780 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0970. Min Act: -0.0001

Data Index: 634880 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0994. Min Act: -0.0001

Data Index: 622914 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0973. Min Act: -0.0001

Data Index: 555815 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0840. Min Act: -0.0001

Data Index: 765498 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1568685 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0950. Min Act: -0.0001

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0798. Min Act: -0.0001

Data Index: 65310 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0889. Min Act: -0.0001

Data Index: 863925 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0843. Min Act: -0.0001

Data Index: 269836 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0894. Min Act: -0.0001

Data Index: 160104 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0878. Min Act: -0.0001

Data Index: 1164406 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0864. Min Act: -0.0001

Data Index: 550441 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1259923 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.0808. Min Act: -0.0001

Data Index: 317170 (C4 (Web Text))

Max Activating Token Index: 185