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

Dataset: The Pile

Neuron 1288 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: 1.4083. Min Range: -1.4083

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1278215 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1438640 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1917334 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1404069 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.2300. Min Act: -0.0000

Data Index: 338675 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.3890. Min Act: -0.0000

Data Index: 767114 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1674886 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1713707 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1830139 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1689440 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1381. Min Act: -0.0000

Data Index: 1618495 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1209865 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1636049 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1722982 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1032. Min Act: -0.0000

Data Index: 483265 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.1398. Min Act: -0.0000

Data Index: 665048 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0754. Min Act: -0.0000

Data Index: 16576 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9414. Min Act: -0.0000

Data Index: 713984 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.4083. Min Range: -1.4083

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1823053 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 1.4083. Min Range: -1.4083

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1598851 (The Pile)

Max Activating Token Index: 464