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

Dataset: The Pile

Neuron 1317 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1833176 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7741. Min Act: -0.0000

Data Index: 550949 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7091. Min Act: -0.0000

Data Index: 758116 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1351703 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1084860 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1766433 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1100529 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1836889 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6590. Min Act: -0.0000

Data Index: 393416 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1004220 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1275449 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1888427 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6571. Min Act: -0.0000

Data Index: 316393 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1334741 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1296370 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6265. Min Act: -0.0000

Data Index: 629007 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6668. Min Act: -0.0000

Data Index: 342881 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1483362 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6443. Min Act: -0.0000

Data Index: 702165 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.7741. Min Range: -0.7741

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1965798 (The Pile)

Max Activating Token Index: 44