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

Dataset: The Pile

Neuron 4550 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.4868. Min Act: -0.0000

Data Index: 1691655 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.2155. Min Act: -0.0000

Data Index: 690334 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 3.4868. Min Range: -3.4868

Max Act: 3.0888. Min Act: -0.0000

Data Index: 33879 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.6769. Min Act: -0.0000

Data Index: 383033 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3037. Min Act: -0.0000

Data Index: 1184027 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3770. Min Act: -0.0000

Data Index: 797341 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.2936. Min Act: -0.0000

Data Index: 216050 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.5525. Min Act: -0.0000

Data Index: 792221 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.1313. Min Act: -0.0000

Data Index: 858640 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.3047. Min Act: -0.0000

Data Index: 745205 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.2684. Min Act: -0.0000

Data Index: 1515174 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.0953. Min Act: -0.0000

Data Index: 1000065 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 3.4868. Min Range: -3.4868

Max Act: 1.9510. Min Act: -0.0000

Data Index: 134769 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.0364. Min Act: -0.0000

Data Index: 453453 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 3.4868. Min Range: -3.4868

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1288471 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.0212. Min Act: -0.0000

Data Index: 303755 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 3.4868. Min Range: -3.4868

Max Act: 2.0763. Min Act: -0.0000

Data Index: 1795407 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 3.4868. Min Range: -3.4868

Max Act: 1.8818. Min Act: -0.0000

Data Index: 246357 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 3.4868. Min Range: -3.4868

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1109603 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 3.4868. Min Range: -3.4868

Max Act: 1.8512. Min Act: -0.0000

Data Index: 469028 (The Pile)

Max Activating Token Index: 100