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

Dataset: The Pile

Neuron 2351 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1031790 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1048213 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6212. Min Act: -0.0000

Data Index: 855849 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7145. Min Act: -0.0000

Data Index: 437757 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1355999 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6060. Min Act: -0.0000

Data Index: 375368 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5696. Min Act: -0.0000

Data Index: 575443 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6322. Min Act: -0.0000

Data Index: 143412 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1835141 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1740748 (The Pile)

Max Activating Token Index: 27

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1834813 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6017. Min Act: -0.0000

Data Index: 461802 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1213887 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1686790 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1983688 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5575. Min Act: -0.0000

Data Index: 769993 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1323937 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1460419 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5575. Min Act: -0.0000

Data Index: 529766 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1753201 (The Pile)

Max Activating Token Index: 757