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

Dataset: The Pile

Neuron 5014 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: 1.2085. Min Range: -1.2085

Max Act: 1.2085. Min Act: -0.0000

Data Index: 844938 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0760. Min Act: -0.0000

Data Index: 473197 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.2081. Min Act: -0.0000

Data Index: 321905 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.1752. Min Act: -0.0000

Data Index: 61376 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.1852. Min Act: -0.0000

Data Index: 55116 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0709. Min Act: -0.0000

Data Index: 908967 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.2085. Min Range: -1.2085

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1402830 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1033728 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1432863 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9390. Min Act: -0.0000

Data Index: 940532 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1749023 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1451670 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1139688 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1311340 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1788520 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1973462 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8941. Min Act: -0.0000

Data Index: 599595 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1730265 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1115323 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.2085. Min Range: -1.2085

Max Act: 0.8783. Min Act: -0.0000

Data Index: 929575 (The Pile)

Max Activating Token Index: 594