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

Dataset: The Pile

Neuron 1370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1572288 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1509028 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7741. Min Act: -0.0000

Data Index: 966623 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7341. Min Act: -0.0000

Data Index: 19904 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7183. Min Act: -0.0000

Data Index: 690052 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6726. Min Act: -0.0000

Data Index: 671239 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6750. Min Act: -0.0000

Data Index: 886224 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1379142 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1923352 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1690649 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7024. Min Act: -0.0000

Data Index: 827205 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1603526 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6631. Min Act: -0.0000

Data Index: 284254 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1034744 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6920. Min Act: -0.0000

Data Index: 457399 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6462. Min Act: -0.0000

Data Index: 616725 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6429. Min Act: -0.0000

Data Index: 750483 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1909837 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6543. Min Act: -0.0000

Data Index: 425278 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6676. Min Act: -0.0000

Data Index: 167739 (The Pile)

Max Activating Token Index: 154