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

Dataset: The Pile

Neuron 1785 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: 0.3028. Min Range: -0.3028

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1514536 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1665093 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1978242 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2945. Min Act: -0.0000

Data Index: 629239 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2562. Min Act: -0.0000

Data Index: 731441 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2099. Min Act: -0.0000

Data Index: 372381 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2402. Min Act: -0.0000

Data Index: 588742 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1977562 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2383. Min Act: -0.0000

Data Index: 277863 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1190493 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2198. Min Act: -0.0000

Data Index: 715847 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2108. Min Act: -0.0000

Data Index: 581642 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1362165 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1439416 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1698967 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1583915 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.1925. Min Act: -0.0000

Data Index: 87558 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1441067 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2132. Min Act: -0.0000

Data Index: 805740 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1496902 (The Pile)

Max Activating Token Index: 1004