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

Dataset: The Pile

Neuron 3757 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: 0.9630. Min Range: -0.9630

Max Act: 0.8328. Min Act: -0.0000

Data Index: 93336 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1225147 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1639935 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7581. Min Act: -0.0000

Data Index: 365006 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1513721 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1469423 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1065782 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1627607 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1624576 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1522352 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1203395 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6120. Min Act: -0.0000

Data Index: 99052 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5793. Min Act: -0.0000

Data Index: 995863 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1407900 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1290919 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.4823. Min Act: -0.0000

Data Index: 544073 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.4426. Min Act: -0.0000

Data Index: 516760 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5217. Min Act: -0.0000

Data Index: 190466 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1816531 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1653718 (The Pile)

Max Activating Token Index: 102