Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.8812. Min Act: -0.0000

Data Index: 1465609 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1945189 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.4693. Min Act: -0.0000

Data Index: 1775898 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2530. Min Act: -0.0000

Data Index: 954738 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3758. Min Act: -0.0000

Data Index: 57811 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.4276. Min Act: -0.0000

Data Index: 448367 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1091329 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1434209 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1821757 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1179441 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2589. Min Act: -0.0000

Data Index: 918985 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1884397 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.1134. Min Act: -0.0000

Data Index: 42128 (The Pile)

Max Activating Token Index: 619

Text #13

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.1407. Min Act: -0.0000

Data Index: 227500 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1794259 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.0977. Min Act: -0.0000

Data Index: 426641 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1315642 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2087. Min Act: -0.0000

Data Index: 105157 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.1597. Min Act: -0.0000

Data Index: 628749 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2177. Min Act: -0.0000

Data Index: 185208 (The Pile)

Max Activating Token Index: 369