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

Dataset: The Pile

Neuron 2854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1763787 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.7233. Min Act: -0.0000

Data Index: 475967 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6553. Min Act: -0.0000

Data Index: 90156 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1260079 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1486830 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6424. Min Act: -0.0000

Data Index: 675866 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1170128 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6609. Min Act: -0.0000

Data Index: 592166 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1846969 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6881. Min Act: -0.0000

Data Index: 439030 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6388. Min Act: -0.0000

Data Index: 508114 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6424. Min Act: -0.0000

Data Index: 894653 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1033717 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6706. Min Act: -0.0000

Data Index: 125872 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6537. Min Act: -0.0000

Data Index: 38844 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1648336 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1971341 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6219. Min Act: -0.0000

Data Index: 187153 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1873041 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.7899. Min Range: -0.7899

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1147230 (The Pile)

Max Activating Token Index: 568