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

Dataset: The Pile

Neuron 2836 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: 1.4811. Min Range: -1.4811

Max Act: 1.4811. Min Act: -0.0000

Data Index: 613913 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1818566 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1456264 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1905020 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.2294. Min Act: -0.0000

Data Index: 108995 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1844852 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.2373. Min Act: -0.0000

Data Index: 67506 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1928742 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0330. Min Act: -0.0000

Data Index: 134779 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0935. Min Act: -0.0000

Data Index: 234481 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0598. Min Act: -0.0000

Data Index: 170908 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0535. Min Act: -0.0000

Data Index: 806618 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0037. Min Act: -0.0000

Data Index: 970951 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 1.4811. Min Range: -1.4811

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1018212 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 1.4811. Min Range: -1.4811

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1658341 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1213201 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.4811. Min Range: -1.4811

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1682743 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 1.4811. Min Range: -1.4811

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1542474 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 1.4811. Min Range: -1.4811

Max Act: 0.9740. Min Act: -0.0000

Data Index: 421179 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 1.4811. Min Range: -1.4811

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1911575 (The Pile)

Max Activating Token Index: 924