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

Dataset: The Pile

Neuron 673 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6944. Min Act: -0.0000

Data Index: 970747 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1470294 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6949. Min Act: -0.0000

Data Index: 30449 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1736047 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1631686 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7233. Min Act: -0.0000

Data Index: 650521 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6549. Min Act: -0.0000

Data Index: 174719 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1045242 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6656. Min Act: -0.0000

Data Index: 60924 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1598586 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 961704 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6935. Min Act: -0.0000

Data Index: 340330 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6472. Min Act: -0.0000

Data Index: 548366 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6301. Min Act: -0.0000

Data Index: 817194 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1110453 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6302. Min Act: -0.0000

Data Index: 640834 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1691653 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6305. Min Act: -0.0000

Data Index: 994299 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1759711 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1772960 (The Pile)

Max Activating Token Index: 484