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

Dataset: The Pile

Neuron 3344 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: 0.5865. Min Range: -0.5865

Max Act: 0.5865. Min Act: -0.0000

Data Index: 761053 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1012963 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1179331 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1421623 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1847131 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5006. Min Act: -0.0000

Data Index: 496517 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1989287 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4530. Min Act: -0.0000

Data Index: 641433 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1452619 (The Pile)

Max Activating Token Index: 845

Text #9

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1441618 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1932175 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4596. Min Act: -0.0000

Data Index: 613230 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4992. Min Act: -0.0000

Data Index: 848967 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4827. Min Act: -0.0000

Data Index: 122127 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1481896 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1927265 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4286. Min Act: -0.0000

Data Index: 378501 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4247. Min Act: -0.0000

Data Index: 43282 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4404. Min Act: -0.0000

Data Index: 95631 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4144. Min Act: -0.0000

Data Index: 578399 (The Pile)

Max Activating Token Index: 274