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

Dataset: The Pile

Neuron 4560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1735732 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0990. Min Act: -0.0000

Data Index: 515405 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0476. Min Act: -0.0000

Data Index: 209885 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1711025 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1166789 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1530266 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9242. Min Act: -0.0000

Data Index: 424072 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0656. Min Act: -0.0000

Data Index: 280696 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9718. Min Act: -0.0000

Data Index: 362866 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1985578 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1826574 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9499. Min Act: -0.0000

Data Index: 29188 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1787666 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1206974 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1069285 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0149. Min Act: -0.0000

Data Index: 522833 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1002443 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9313. Min Act: -0.0000

Data Index: 125604 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8912. Min Act: -0.0000

Data Index: 392855 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1493248 (The Pile)

Max Activating Token Index: 796