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

Dataset: The Pile

Neuron 2471 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: 1.2683. Min Range: -1.2683

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1761347 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1331400 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1185291 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1995709 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1404442 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1253335 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9410. Min Act: -0.0000

Data Index: 819033 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1796280 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0544. Min Act: -0.0000

Data Index: 932403 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1026566 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9656. Min Act: -0.0000

Data Index: 952342 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1075505 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9199. Min Act: -0.0000

Data Index: 75131 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0736. Min Act: -0.0000

Data Index: 822220 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0114. Min Act: -0.0000

Data Index: 831500 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0441. Min Act: -0.0000

Data Index: 88067 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1259450 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1746813 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.2683. Min Range: -1.2683

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1721546 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 1.2683. Min Range: -1.2683

Max Act: 0.9745. Min Act: -0.0000

Data Index: 401663 (The Pile)

Max Activating Token Index: 297