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

Dataset: The Pile

Neuron 1511 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.5882. Min Act: -0.0000

Data Index: 47757 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 3.6629. Min Range: -3.6629

Max Act: 3.6629. Min Act: -0.0000

Data Index: 1191381 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0988. Min Act: -0.0000

Data Index: 852901 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.2421. Min Act: -0.0000

Data Index: 1444233 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.2099. Min Act: -0.0000

Data Index: 1892042 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0767. Min Act: -0.0000

Data Index: 980855 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8191. Min Act: -0.0000

Data Index: 1233643 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.9875. Min Act: -0.0000

Data Index: 1493841 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 3.6629. Min Range: -3.6629

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1400133 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.9491. Min Act: -0.0000

Data Index: 1913044 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8302. Min Act: -0.0000

Data Index: 581292 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1348082 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7911. Min Act: -0.0000

Data Index: 1411415 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.9931. Min Act: -0.0000

Data Index: 1603405 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8246. Min Act: -0.0000

Data Index: 1732676 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.8478. Min Act: -0.0000

Data Index: 970180 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7884. Min Act: -0.0000

Data Index: 1256993 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1788519 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7589. Min Act: 0.0000

Data Index: 969075 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.6629. Min Range: -3.6629

Max Act: 1.7410. Min Act: -0.0000

Data Index: 128895 (The Pile)

Max Activating Token Index: 49