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

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

Neuron 6055 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1307. Min Range: -1.1307

Max Act: 1.1307. Min Act: -0.0000

Data Index: 330843 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1314789 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7925. Min Act: -0.0000

Data Index: 466432 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7629. Min Act: -0.0000

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7889. Min Act: -0.0000

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1378567 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.8434. Min Act: -0.0000

Data Index: 584193 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1251356 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7914. Min Act: -0.0000

Data Index: 565725 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7809. Min Act: -0.0000

Data Index: 656882 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7001. Min Act: -0.0000

Data Index: 963151 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7655. Min Act: -0.0000

Data Index: 574821 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.7442. Min Act: -0.0000

Data Index: 612094 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6740. Min Act: -0.0000

Data Index: 633553 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6584. Min Act: -0.0000

Data Index: 756636 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1059560 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1316784 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6539. Min Act: -0.0000

Data Index: 138694 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1463836 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 1.1307. Min Range: -1.1307

Max Act: 0.6459. Min Act: -0.0000

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 495