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

Dataset: The Pile

Neuron 2436 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: 1.5274. Min Range: -1.5274

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1266584 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1963972 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.2771. Min Act: -0.0000

Data Index: 861295 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1637. Min Act: -0.0000

Data Index: 657775 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1352408 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1674067 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1951. Min Act: -0.0000

Data Index: 891294 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1019011 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1695270 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1391464 (The Pile)

Max Activating Token Index: 659

Text #10

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1333711 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.1402. Min Act: -0.0000

Data Index: 333910 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1708955 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.5274. Min Range: -1.5274

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1049787 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1665771 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9477. Min Act: -0.0000

Data Index: 585575 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1340345 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1757559 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.8901. Min Act: -0.0000

Data Index: 796415 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 1.5274. Min Range: -1.5274

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1342965 (The Pile)

Max Activating Token Index: 755