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

Dataset: The Pile

Neuron 1820 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: 0.8584. Min Range: -0.8584

Max Act: 0.8584. Min Act: -0.0000

Data Index: 95107 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7947. Min Act: -0.0000

Data Index: 329231 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1617767 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7330. Min Act: -0.0000

Data Index: 519317 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1037681 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7631. Min Act: -0.0000

Data Index: 321858 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1617146 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1927926 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7273. Min Act: -0.0000

Data Index: 591791 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7245. Min Act: -0.0000

Data Index: 857326 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6634. Min Act: -0.0000

Data Index: 703147 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7109. Min Act: -0.0000

Data Index: 21189 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6627. Min Act: -0.0000

Data Index: 351131 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6995. Min Act: -0.0000

Data Index: 776497 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1920504 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1133416 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1152297 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6838. Min Act: -0.0000

Data Index: 637239 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6438. Min Act: -0.0000

Data Index: 39842 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.7014. Min Act: -0.0000

Data Index: 341081 (The Pile)

Max Activating Token Index: 439