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

Dataset: The Pile

Neuron 69 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: 1.3134. Min Range: -1.3134

Max Act: 1.3134. Min Act: -0.0000

Data Index: 386339 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0967. Min Act: -0.0000

Data Index: 166944 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.1502. Min Act: -0.0000

Data Index: 554025 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1364017 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1621565 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0085. Min Act: -0.0000

Data Index: 895242 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1651849 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1044993 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0191. Min Act: -0.0000

Data Index: 64248 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0785. Min Act: -0.0000

Data Index: 473107 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1395291 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 1.3134. Min Range: -1.3134

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1483720 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1120777 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1207976 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9807. Min Act: -0.0000

Data Index: 869186 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1305834 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1714704 (The Pile)

Max Activating Token Index: 534

Text #17

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9248. Min Act: -0.0000

Data Index: 844990 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9921. Min Act: -0.0000

Data Index: 977411 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.3134. Min Range: -1.3134

Max Act: 0.9574. Min Act: -0.0000

Data Index: 467287 (The Pile)

Max Activating Token Index: 359