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

Dataset: The Pile

Neuron 1831 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5482. Min Range: -3.5482

Max Act: 3.5482. Min Act: -0.0000

Data Index: 1132778 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 3.5482. Min Range: -3.5482

Max Act: 3.3115. Min Act: -0.0000

Data Index: 1448825 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 3.5482. Min Range: -3.5482

Max Act: 3.1868. Min Act: -0.0000

Data Index: 201381 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 3.5482. Min Range: -3.5482

Max Act: 3.0683. Min Act: -0.0000

Data Index: 432397 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 3.5482. Min Range: -3.5482

Max Act: 3.0019. Min Act: -0.0000

Data Index: 1184811 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.9646. Min Act: -0.0000

Data Index: 52054 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.9393. Min Act: -0.0000

Data Index: 721177 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.7808. Min Act: -0.0000

Data Index: 1863990 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.7374. Min Act: -0.0000

Data Index: 995859 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.9649. Min Act: -0.0000

Data Index: 362756 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1031706 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.6379. Min Act: -0.0000

Data Index: 1805089 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.7735. Min Act: -0.0000

Data Index: 1606765 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.8577. Min Act: -0.0000

Data Index: 701748 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.5914. Min Act: -0.0000

Data Index: 533243 (The Pile)

Max Activating Token Index: 931

Text #15

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.3614. Min Act: -0.0000

Data Index: 1485668 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.6624. Min Act: -0.0000

Data Index: 106084 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1432259 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.5807. Min Act: -0.0000

Data Index: 1417395 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 3.5482. Min Range: -3.5482

Max Act: 2.5785. Min Act: -0.0000

Data Index: 1298091 (The Pile)

Max Activating Token Index: 89