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

Dataset: The Pile

Neuron 3051 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: 0.7701. Min Range: -0.7701

Max Act: 0.7518. Min Act: -0.0000

Data Index: 882830 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7044. Min Act: -0.0000

Data Index: 597725 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1431856 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1820755 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1696742 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1733628 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6921. Min Act: -0.0000

Data Index: 531086 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6487. Min Act: -0.0000

Data Index: 392514 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6650. Min Act: -0.0000

Data Index: 320752 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6429. Min Act: -0.0000

Data Index: 342118 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1828511 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6083. Min Act: -0.0000

Data Index: 807198 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6266. Min Act: -0.0000

Data Index: 6837 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1341296 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6403. Min Act: -0.0000

Data Index: 469196 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1723006 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1318344 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1456532 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1887863 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1943132 (The Pile)

Max Activating Token Index: 314