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

Dataset: The Pile

Neuron 4101 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: 0.9335. Min Range: -0.9335

Max Act: 0.9335. Min Act: -0.0000

Data Index: 441845 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8099. Min Act: -0.0000

Data Index: 145844 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8183. Min Act: -0.0000

Data Index: 498703 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8875. Min Act: -0.0000

Data Index: 402727 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8115. Min Act: -0.0000

Data Index: 5215 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1313004 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1067424 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1300124 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8093. Min Act: -0.0000

Data Index: 218191 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7536. Min Act: -0.0000

Data Index: 741366 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7886. Min Act: -0.0000

Data Index: 135959 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1750709 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7089. Min Act: -0.0000

Data Index: 36764 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7262. Min Act: -0.0000

Data Index: 794807 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1176411 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7474. Min Act: -0.0000

Data Index: 696158 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7413. Min Act: -0.0000

Data Index: 189217 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7613. Min Act: -0.0000

Data Index: 558325 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1183050 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1500563 (The Pile)

Max Activating Token Index: 322