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

Dataset: The Pile

Neuron 3474 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: 3.7872. Min Range: -3.7872

Max Act: 3.6583. Min Act: -0.0000

Data Index: 1294297 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.7872. Min Act: -0.0000

Data Index: 74659 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.4531. Min Act: -0.0000

Data Index: 1137495 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.6540. Min Act: -0.0000

Data Index: 516979 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.3044. Min Act: -0.0000

Data Index: 1369005 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.3608. Min Act: -0.0000

Data Index: 157702 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.4431. Min Act: -0.0000

Data Index: 1763481 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.1530. Min Act: -0.0000

Data Index: 1787433 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.2756. Min Act: -0.0000

Data Index: 1652468 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.9705. Min Act: -0.0000

Data Index: 875569 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.1003. Min Act: -0.0000

Data Index: 136017 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.0187. Min Act: -0.0000

Data Index: 459816 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.0517. Min Act: -0.0000

Data Index: 1946395 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.0644. Min Act: -0.0000

Data Index: 1639268 (The Pile)

Max Activating Token Index: 956

Text #14

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.8855. Min Act: -0.0000

Data Index: 1635164 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.9850. Min Act: -0.0000

Data Index: 309448 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.6571. Min Act: -0.0000

Data Index: 74393 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.9599. Min Act: -0.0000

Data Index: 1447518 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 3.7872. Min Range: -3.7872

Max Act: 2.7662. Min Act: -0.0000

Data Index: 1393142 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 3.7872. Min Range: -3.7872

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1915357 (The Pile)

Max Activating Token Index: 726