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

Dataset: The Pile

Neuron 3789 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0000

Data Index: 631014 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5943. Min Act: -0.0000

Data Index: 634803 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1188386 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5387. Min Act: -0.0000

Data Index: 159987 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1575636 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1976689 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1086599 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1884170 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1313736 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1512467 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1267351 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4796. Min Act: -0.0000

Data Index: 116664 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1048749 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4727. Min Act: -0.0000

Data Index: 144126 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4703. Min Act: 0.0000

Data Index: 1093883 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1705298 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1749135 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4573. Min Act: -0.0000

Data Index: 971449 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5047. Min Act: -0.0000

Data Index: 860416 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1265610 (The Pile)

Max Activating Token Index: 700