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

Dataset: The Pile

Neuron 3892 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: 3.1677. Min Range: -3.1677

Max Act: 3.1677. Min Act: -0.0000

Data Index: 1271765 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.6609. Min Act: -0.0000

Data Index: 1081885 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.1625. Min Act: -0.0000

Data Index: 892764 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.4052. Min Act: -0.0000

Data Index: 1438348 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.2630. Min Act: -0.0000

Data Index: 821955 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 3.1677. Min Range: -3.1677

Max Act: 2.0440. Min Act: -0.0000

Data Index: 862744 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1321924 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.8988. Min Act: -0.0000

Data Index: 932459 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1408736 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.9801. Min Act: -0.0000

Data Index: 1679794 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5303. Min Act: -0.0000

Data Index: 1363752 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.6502. Min Act: -0.0000

Data Index: 622289 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.8919. Min Act: -0.0000

Data Index: 1889696 (The Pile)

Max Activating Token Index: 750

Text #13

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1106838 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.6644. Min Act: -0.0000

Data Index: 886849 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5792. Min Act: -0.0000

Data Index: 871435 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1347657 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1059243 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1575873 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 3.1677. Min Range: -3.1677

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1489573 (The Pile)

Max Activating Token Index: 572