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

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

Neuron 3006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0000

Data Index: 366897 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1232412 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1217703 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0963. Min Act: -0.0000

Data Index: 536386 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0937. Min Act: -0.0000

Data Index: 960839 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0878. Min Act: -0.0001

Data Index: 652994 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0811. Min Act: -0.0001

Data Index: 404299 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0883. Min Act: -0.0000

Data Index: 256966 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0891. Min Act: -0.0000

Data Index: 393912 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0905. Min Act: -0.0000

Data Index: 239786 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0877. Min Act: -0.0000

Data Index: 341416 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0776. Min Act: -0.0000

Data Index: 901384 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0868. Min Act: -0.0000

Data Index: 756762 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1463080 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1051015 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1322932 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0859. Min Act: -0.0001

Data Index: 658409 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0882. Min Act: -0.0000

Data Index: 522703 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1309245 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0818. Min Act: -0.0001

Data Index: 153689 (C4 (Web Text))

Max Activating Token Index: 181