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

Dataset: The Pile

Neuron 3931 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1646812 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1964695 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1316893 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4559. Min Act: -0.0000

Data Index: 696386 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4406. Min Act: -0.0000

Data Index: 351861 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1456407 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4122. Min Act: -0.0000

Data Index: 810118 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1204444 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3736. Min Act: 0.0000

Data Index: 1075811 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4143. Min Act: -0.0000

Data Index: 767341 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1104282 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3619. Min Act: -0.0000

Data Index: 64442 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3579. Min Act: 0.0000

Data Index: 944121 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1078220 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3999. Min Act: -0.0000

Data Index: 290235 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1989742 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3417. Min Act: -0.0000

Data Index: 301543 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1647357 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3462. Min Act: -0.0000

Data Index: 159636 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3763. Min Act: -0.0000

Data Index: 935693 (The Pile)

Max Activating Token Index: 176