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

Dataset: The Pile

Neuron 1936 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: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1909549 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1355783 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1723237 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1827074 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1210533 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1708923 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1884920 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9766. Min Act: -0.0000

Data Index: 69613 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0929. Min Act: -0.0000

Data Index: 57122 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0069. Min Act: -0.0000

Data Index: 996374 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0221. Min Act: -0.0000

Data Index: 680151 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0794. Min Act: -0.0000

Data Index: 527519 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1565683 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9841. Min Act: -0.0000

Data Index: 245136 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0205. Min Act: -0.0000

Data Index: 863221 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0090. Min Act: -0.0000

Data Index: 371482 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1986100 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1246719 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0334. Min Act: -0.0000

Data Index: 335797 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9715. Min Act: -0.0000

Data Index: 321528 (The Pile)

Max Activating Token Index: 26