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

Dataset: The Pile

Neuron 4868 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: 5.4490. Min Range: -5.4490

Max Act: 5.4490. Min Act: -0.0000

Data Index: 1845896 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.6393. Min Act: -0.0000

Data Index: 1058575 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.4746. Min Act: -0.0000

Data Index: 483556 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.7334. Min Act: -0.0000

Data Index: 1521629 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.7551. Min Act: -0.0000

Data Index: 1511837 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.1384. Min Act: -0.0000

Data Index: 1208785 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.8427. Min Act: -0.0000

Data Index: 347633 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.6452. Min Act: -0.0000

Data Index: 964561 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.6463. Min Act: -0.0000

Data Index: 133846 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.8208. Min Act: -0.0000

Data Index: 1763580 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.6379. Min Act: -0.0000

Data Index: 1969368 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.6246. Min Act: -0.0000

Data Index: 924421 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.4522. Min Act: -0.0000

Data Index: 734749 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.4340. Min Act: -0.0000

Data Index: 1900233 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.5966. Min Act: -0.0000

Data Index: 331397 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.3872. Min Act: -0.0000

Data Index: 1604715 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.3875. Min Act: -0.0000

Data Index: 1045395 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.1825. Min Act: -0.0000

Data Index: 1081950 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.5263. Min Act: -0.0000

Data Index: 1440400 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 5.4490. Min Range: -5.4490

Max Act: 4.3543. Min Act: -0.0000

Data Index: 711937 (The Pile)

Max Activating Token Index: 833