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

Dataset: The Pile

Neuron 4727 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: 0.8475. Min Range: -0.8475

Max Act: 0.8253. Min Act: -0.0000

Data Index: 380591 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1219301 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7855. Min Act: -0.0000

Data Index: 81732 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1359657 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8064. Min Act: -0.0000

Data Index: 577160 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7779. Min Act: -0.0000

Data Index: 494033 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1304174 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1420592 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1814190 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.8475. Min Act: -0.0000

Data Index: 120524 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7574. Min Act: -0.0000

Data Index: 372669 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1055966 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1270916 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1596666 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1758869 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7538. Min Act: -0.0000

Data Index: 273441 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7285. Min Act: -0.0000

Data Index: 716737 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1411025 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7609. Min Act: -0.0000

Data Index: 463613 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.8475. Min Range: -0.8475

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1900283 (The Pile)

Max Activating Token Index: 308