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

Dataset: The Pile

Neuron 4575 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1099615 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1166900 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1198899 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9143. Min Act: -0.0000

Data Index: 631359 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1843595 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1228842 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1114170 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1982738 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7935. Min Act: -0.0000

Data Index: 826356 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7861. Min Act: -0.0000

Data Index: 688304 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1519191 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8142. Min Act: -0.0000

Data Index: 395517 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8673. Min Act: -0.0000

Data Index: 246189 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8372. Min Act: -0.0000

Data Index: 375979 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8122. Min Act: -0.0000

Data Index: 872272 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1938415 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1830414 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8559. Min Act: -0.0000

Data Index: 104775 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1062206 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7962. Min Act: -0.0000

Data Index: 427461 (The Pile)

Max Activating Token Index: 421