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

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

Neuron 3285 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: 0.2110. Min Range: -0.2110

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1229454 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.2092. Min Act: -0.0001

Data Index: 1300858 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1325583 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1719. Min Act: -0.0001

Data Index: 491464 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1718. Min Act: -0.0001

Data Index: 378707 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1033061 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1087227 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1729. Min Act: -0.0001

Data Index: 23701 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1610. Min Act: -0.0001

Data Index: 669061 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1522151 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1451. Min Act: -0.0001

Data Index: 331242 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1486. Min Act: -0.0001

Data Index: 655658 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1491. Min Act: -0.0001

Data Index: 301734 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1447. Min Act: -0.0001

Data Index: 981490 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1435. Min Act: -0.0001

Data Index: 415357 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1434. Min Act: -0.0001

Data Index: 304786 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1352. Min Act: -0.0001

Data Index: 23838 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1307. Min Act: -0.0001

Data Index: 764144 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1365. Min Act: -0.0001

Data Index: 89790 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1343575 (C4 (Web Text))

Max Activating Token Index: 505