Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5975 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2883. Min Range: -4.2883

Max Act: 4.2883. Min Act: -0.0000

Data Index: 769780 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.6903. Min Act: -0.0000

Data Index: 1011771 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.6493. Min Act: -0.0000

Data Index: 189027 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.6455. Min Act: -0.0000

Data Index: 150510 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.9141. Min Act: -0.0000

Data Index: 859974 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.5891. Min Act: -0.0000

Data Index: 780793 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.8789. Min Act: -0.0000

Data Index: 76861 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.7047. Min Act: -0.0000

Data Index: 777861 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.6446. Min Act: -0.0000

Data Index: 948200 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.5382. Min Act: -0.0000

Data Index: 1284250 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.5657. Min Act: -0.0000

Data Index: 990000 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.5062. Min Act: -0.0000

Data Index: 1572700 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1336189 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.5086. Min Act: -0.0000

Data Index: 972312 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.3763. Min Act: -0.0000

Data Index: 92124 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1164321 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.1934. Min Act: -0.0000

Data Index: 1331852 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.3243. Min Act: -0.0000

Data Index: 668863 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.3321. Min Act: -0.0000

Data Index: 636394 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.2904. Min Act: -0.0000

Data Index: 559011 (C4 (Web Text))

Max Activating Token Index: 251