Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1319009 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9953. Min Act: -0.0000

Data Index: 67382 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1598797 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8642. Min Act: -0.0000

Data Index: 518522 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1679813 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8130. Min Act: -0.0000

Data Index: 698387 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7596. Min Act: -0.0000

Data Index: 322935 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7950. Min Act: -0.0000

Data Index: 907233 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1727645 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1697128 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7222. Min Act: -0.0000

Data Index: 635943 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1446944 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7580. Min Act: -0.0000

Data Index: 776798 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8116. Min Act: -0.0000

Data Index: 261582 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6865. Min Act: -0.0000

Data Index: 408858 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8509. Min Act: -0.0000

Data Index: 944263 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7434. Min Act: -0.0000

Data Index: 810773 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1460180 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7443. Min Act: -0.0000

Data Index: 15045 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.6850. Min Act: -0.0000

Data Index: 565125 (The Pile)

Max Activating Token Index: 166