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

Dataset: The Pile

Neuron 26 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.4883. Min Act: -0.0000

Data Index: 313656 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.4532. Min Act: -0.0000

Data Index: 1302607 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3859. Min Act: -0.0000

Data Index: 1750404 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.2139. Min Act: -0.0000

Data Index: 1515633 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.0507. Min Act: -0.0000

Data Index: 641588 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.3280. Min Act: -0.0000

Data Index: 1524707 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.8047. Min Act: -0.0000

Data Index: 473548 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.1925. Min Act: -0.0000

Data Index: 1281470 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.0959. Min Act: -0.0000

Data Index: 1412890 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9485. Min Act: -0.0000

Data Index: 408366 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.0773. Min Act: -0.0000

Data Index: 167567 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.0525. Min Act: -0.0000

Data Index: 1783787 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.0076. Min Act: -0.0000

Data Index: 1006577 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.8799. Min Act: -0.0000

Data Index: 362505 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9560. Min Act: -0.0000

Data Index: 1437117 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 3.4883. Min Range: -3.4883

Max Act: 3.1162. Min Act: -0.0000

Data Index: 1845649 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9825. Min Act: -0.0000

Data Index: 1058504 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9775. Min Act: -0.0000

Data Index: 1896104 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9678. Min Act: -0.0000

Data Index: 1859291 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 3.4883. Min Range: -3.4883

Max Act: 2.9540. Min Act: -0.0000

Data Index: 1042951 (The Pile)

Max Activating Token Index: 556