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

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

Neuron 1094 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1332250 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1446240 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0698. Min Act: -0.0002

Data Index: 769157 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1003934 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1359893 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1648255 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1535839 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0571. Min Act: -0.0002

Data Index: 471955 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1414865 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0508. Min Act: -0.0002

Data Index: 608896 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0521. Min Act: -0.0002

Data Index: 781377 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1462193 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0585. Min Act: -0.0002

Data Index: 810188 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1041473 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1000844 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1489887 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0522. Min Act: -0.0002

Data Index: 884613 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1655802 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1012286 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0574. Min Act: -0.0002

Data Index: 165421 (C4 (Web Text))

Max Activating Token Index: 957