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

Dataset: The Pile

Neuron 3407 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: 5.2115. Min Range: -5.2115

Max Act: 5.2115. Min Act: -0.0000

Data Index: 902774 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.8075. Min Act: -0.0000

Data Index: 1839647 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 5.2115. Min Range: -5.2115

Max Act: 5.1734. Min Act: -0.0000

Data Index: 1936578 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 5.2115. Min Range: -5.2115

Max Act: 5.0900. Min Act: -0.0000

Data Index: 839810 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 5.2115. Min Range: -5.2115

Max Act: 5.0041. Min Act: -0.0000

Data Index: 1644056 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6411. Min Act: -0.0000

Data Index: 882896 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6967. Min Act: -0.0000

Data Index: 1090591 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.4922. Min Act: -0.0000

Data Index: 899732 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6422. Min Act: -0.0000

Data Index: 1043111 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6298. Min Act: -0.0000

Data Index: 1471124 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.7602. Min Act: -0.0000

Data Index: 1403456 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.5610. Min Act: -0.0000

Data Index: 1623004 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.7173. Min Act: -0.0000

Data Index: 1667154 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6980. Min Act: -0.0000

Data Index: 148038 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.5516. Min Act: -0.0000

Data Index: 1255645 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.5403. Min Act: -0.0000

Data Index: 1723056 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.4954. Min Act: -0.0000

Data Index: 481174 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.5167. Min Act: -0.0000

Data Index: 527529 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.4807. Min Act: -0.0000

Data Index: 1387065 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 5.2115. Min Range: -5.2115

Max Act: 4.6631. Min Act: -0.0000

Data Index: 1201172 (The Pile)

Max Activating Token Index: 192