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

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

Neuron 525 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: 0.2321. Min Range: -0.2321

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1527689 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1370577 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2029. Min Act: -0.0000

Data Index: 664198 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1120382 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2021. Min Act: -0.0000

Data Index: 873991 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2111. Min Act: -0.0000

Data Index: 134782 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1877. Min Act: -0.0000

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1541182 (Python Code)

Max Activating Token Index: 341

Text #8

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2017. Min Act: -0.0000

Data Index: 355730 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1531939 (Python Code)

Max Activating Token Index: 707

Text #10

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1639107 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1836. Min Act: -0.0000

Data Index: 427113 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1541208 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1511737 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1445353 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1582558 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1513905 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1559020 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1606506 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1503627 (Python Code)

Max Activating Token Index: 192