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

Dataset: The Pile

Neuron 4599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1865178 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.6391. Min Act: -0.0000

Data Index: 584912 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5693. Min Act: 0.0000

Data Index: 1671131 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5987. Min Act: -0.0000

Data Index: 705144 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5155. Min Act: -0.0000

Data Index: 803569 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5589. Min Act: -0.0000

Data Index: 584536 (The Pile)

Max Activating Token Index: 857

Text #6

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5648. Min Act: -0.0000

Data Index: 642376 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1794632 (The Pile)

Max Activating Token Index: 599

Text #8

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1822421 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1214257 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4928. Min Act: 0.0000

Data Index: 1704373 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1608836 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5196. Min Act: -0.0000

Data Index: 491479 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5345. Min Act: -0.0000

Data Index: 932284 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5325. Min Act: -0.0000

Data Index: 744171 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1676345 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1755327 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1262571 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5423. Min Act: -0.0000

Data Index: 241489 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1929889 (The Pile)

Max Activating Token Index: 161