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

Dataset: The Pile

Neuron 4992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1860271 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.9637. Min Act: -0.0000

Data Index: 451002 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1072697 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1774726 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1316322 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7876. Min Act: -0.0000

Data Index: 450810 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1585250 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8789. Min Act: -0.0000

Data Index: 752310 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8099. Min Act: -0.0000

Data Index: 433915 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7490. Min Act: -0.0000

Data Index: 35164 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8183. Min Act: -0.0000

Data Index: 681132 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1508941 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8686. Min Act: -0.0000

Data Index: 398669 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.8729. Min Act: -0.0000

Data Index: 901947 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7906. Min Act: -0.0000

Data Index: 793692 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1712742 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7794. Min Act: -0.0001

Data Index: 575536 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1515082 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1937127 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.9824. Min Range: -0.9824

Max Act: 0.7700. Min Act: -0.0000

Data Index: 241217 (The Pile)

Max Activating Token Index: 241