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

Dataset: The Pile

Neuron 3554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1707461 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1565. Min Act: -0.0000

Data Index: 286431 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.7711. Min Act: -0.0000

Data Index: 893599 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0059. Min Act: -0.0000

Data Index: 249543 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9145. Min Act: -0.0000

Data Index: 393085 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1076739 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9683. Min Act: -0.0001

Data Index: 939848 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1850565 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1071593 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9348. Min Act: -0.0000

Data Index: 504863 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9031. Min Act: -0.0000

Data Index: 408690 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9035. Min Act: -0.0000

Data Index: 19452 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8387. Min Act: -0.0000

Data Index: 641382 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1362103 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8635. Min Act: -0.0000

Data Index: 390066 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8385. Min Act: -0.0000

Data Index: 474759 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8069. Min Act: -0.0000

Data Index: 950289 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1492182 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1126708 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.7703. Min Act: -0.0000

Data Index: 729917 (The Pile)

Max Activating Token Index: 297