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

Dataset: The Pile

Neuron 3241 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: 1.8773. Min Range: -1.8773

Max Act: 1.8773. Min Act: -0.0000

Data Index: 997978 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7411. Min Act: -0.0000

Data Index: 472052 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7090. Min Act: -0.0000

Data Index: 161357 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7058. Min Act: -0.0000

Data Index: 714156 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1605936 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7776. Min Act: -0.0000

Data Index: 857650 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.6672. Min Act: -0.0000

Data Index: 353106 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7509. Min Act: -0.0000

Data Index: 1204817 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7455. Min Act: -0.0000

Data Index: 811116 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.8118. Min Act: -0.0000

Data Index: 765597 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7336. Min Act: -0.0000

Data Index: 1228714 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7647. Min Act: -0.0000

Data Index: 1113249 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1969524 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.6573. Min Act: -0.0000

Data Index: 1507403 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.7174. Min Act: -0.0000

Data Index: 10196 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1093376 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.5513. Min Act: -0.0000

Data Index: 933728 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.6182. Min Act: -0.0000

Data Index: 1295518 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.6829. Min Act: -0.0000

Data Index: 884511 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.6043. Min Act: -0.0000

Data Index: 644670 (The Pile)

Max Activating Token Index: 627