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

Dataset: The Pile

Neuron 831 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: 0.7714. Min Range: -0.7714

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1360687 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1137329 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1856298 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1164642 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1422904 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1866177 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5438. Min Act: -0.0000

Data Index: 860784 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1023817 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1509494 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5383. Min Act: -0.0000

Data Index: 208037 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5346. Min Act: -0.0000

Data Index: 76861 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5328. Min Act: -0.0000

Data Index: 540500 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5325. Min Act: -0.0000

Data Index: 726128 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5643. Min Act: -0.0000

Data Index: 463650 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5108. Min Act: -0.0000

Data Index: 654530 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1118794 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1259726 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5255. Min Act: -0.0000

Data Index: 848883 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1837464 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.7714. Min Range: -0.7714

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1590162 (The Pile)

Max Activating Token Index: 488