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

Dataset: The Pile

Neuron 4400 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: 3.4624. Min Range: -3.4624

Max Act: 3.4624. Min Act: -0.0000

Data Index: 587638 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.8193. Min Act: -0.0000

Data Index: 42716 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 3.4624. Min Range: -3.4624

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1060487 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.5344. Min Act: -0.0000

Data Index: 1967868 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.7357. Min Act: -0.0000

Data Index: 1263833 (The Pile)

Max Activating Token Index: 499

Text #5

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.4758. Min Act: -0.0000

Data Index: 1184364 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1614265 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.2652. Min Act: -0.0000

Data Index: 779880 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.4690. Min Act: -0.0000

Data Index: 1288612 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.3397. Min Act: -0.0000

Data Index: 664121 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.3016. Min Act: -0.0000

Data Index: 1160206 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.4087. Min Act: -0.0000

Data Index: 1105524 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.2886. Min Act: -0.0000

Data Index: 303475 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1386767 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.3469. Min Act: -0.0000

Data Index: 855854 (The Pile)

Max Activating Token Index: 243

Text #15

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.3042. Min Act: -0.0000

Data Index: 51877 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.3433. Min Act: -0.0000

Data Index: 280811 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.0794. Min Act: -0.0000

Data Index: 1753811 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 3.4624. Min Range: -3.4624

Max Act: 2.0826. Min Act: -0.0000

Data Index: 83822 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 3.4624. Min Range: -3.4624

Max Act: 1.9543. Min Act: -0.0000

Data Index: 89346 (The Pile)

Max Activating Token Index: 799