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

Dataset: The Pile

Neuron 729 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0000

Data Index: 839742 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1831905 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6286. Min Act: -0.0000

Data Index: 555041 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5838. Min Act: -0.0000

Data Index: 578634 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5931. Min Act: -0.0000

Data Index: 577060 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1229059 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1728663 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5775. Min Act: -0.0000

Data Index: 611526 (The Pile)

Max Activating Token Index: 113

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1473469 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1712991 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5546. Min Act: -0.0000

Data Index: 36027 (The Pile)

Max Activating Token Index: 682

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5691. Min Act: -0.0000

Data Index: 182008 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1689696 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1798801 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1198426 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1560871 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1439121 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1443236 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1182774 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1363255 (The Pile)

Max Activating Token Index: 328