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

Dataset: The Pile

Neuron 406 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1118347 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1700952 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7355. Min Act: 0.0000

Data Index: 1103956 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8078. Min Act: 0.0000

Data Index: 972222 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8251. Min Act: -0.0000

Data Index: 977377 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8222. Min Act: -0.0000

Data Index: 532302 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1806693 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6965. Min Act: 0.0000

Data Index: 1337604 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6590. Min Act: -0.0000

Data Index: 633742 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1989480 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1490009 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1195286 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1074730 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1794080 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5996. Min Act: -0.0000

Data Index: 313695 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1922687 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1423190 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1760249 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6193. Min Act: -0.0000

Data Index: 833554 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.4909. Min Act: -0.0000

Data Index: 230054 (The Pile)

Max Activating Token Index: 296