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

Dataset: The Pile

Neuron 3021 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: 1.8537. Min Range: -1.8537

Max Act: 1.8537. Min Act: -0.0000

Data Index: 270145 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6476. Min Act: -0.0000

Data Index: 663762 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6224. Min Act: -0.0000

Data Index: 667439 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6114. Min Act: -0.0000

Data Index: 1643099 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1906199 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1851231 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1233549 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6437. Min Act: -0.0000

Data Index: 1301913 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1607926 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.6143. Min Act: -0.0000

Data Index: 1938662 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1840164 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5180. Min Act: -0.0000

Data Index: 721416 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.4354. Min Act: -0.0000

Data Index: 293908 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5858. Min Act: -0.0000

Data Index: 1452754 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1289006 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.4938. Min Act: -0.0000

Data Index: 461356 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1485550 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5749. Min Act: -0.0000

Data Index: 1048740 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1262597 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 1.8537. Min Range: -1.8537

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1102205 (The Pile)

Max Activating Token Index: 310