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

Dataset: The Pile

Neuron 693 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: 0.7874. Min Range: -0.7874

Max Act: 0.7701. Min Act: -0.0000

Data Index: 4585 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1504896 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1822079 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7064. Min Act: -0.0000

Data Index: 365939 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1494308 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7082. Min Act: -0.0000

Data Index: 978717 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.7228. Min Act: -0.0000

Data Index: 464450 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5988. Min Act: -0.0000

Data Index: 582708 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6903. Min Act: -0.0000

Data Index: 798656 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1741509 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1686942 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5653. Min Act: -0.0000

Data Index: 150365 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1931912 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5237. Min Act: -0.0000

Data Index: 314335 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1377739 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1326431 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1164402 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6090. Min Act: -0.0000

Data Index: 727799 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.6231. Min Act: -0.0000

Data Index: 691480 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.7874. Min Range: -0.7874

Max Act: 0.4495. Min Act: -0.0000

Data Index: 596123 (The Pile)

Max Activating Token Index: 912