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

Dataset: The Pile

Neuron 796 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1644490 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5817. Min Act: 0.0000

Data Index: 1221257 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5957. Min Act: -0.0000

Data Index: 647406 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1891018 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1324197 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5591. Min Act: -0.0000

Data Index: 432013 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1139676 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5460. Min Act: -0.0000

Data Index: 44572 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1465175 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5487. Min Act: -0.0000

Data Index: 860730 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5104. Min Act: -0.0000

Data Index: 713887 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4948. Min Act: -0.0000

Data Index: 765273 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4675. Min Act: 0.0000

Data Index: 1722406 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5106. Min Act: 0.0000

Data Index: 565093 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1038803 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1401376 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5103. Min Act: -0.0000

Data Index: 302944 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4891. Min Act: -0.0000

Data Index: 11271 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4691. Min Act: -0.0000

Data Index: 999480 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4752. Min Act: -0.0000

Data Index: 622211 (The Pile)

Max Activating Token Index: 293