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

Dataset: The Pile

Neuron 3559 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: 1.3876. Min Range: -1.3876

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1705038 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1368256 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0700. Min Act: 0.0000

Data Index: 119750 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1658540 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1307253 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0129. Min Act: -0.0000

Data Index: 534124 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1490861 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9163. Min Act: -0.0000

Data Index: 980176 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1610708 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1265744 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9090. Min Act: -0.0000

Data Index: 407294 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9455. Min Act: 0.0000

Data Index: 1759742 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8432. Min Act: -0.0000

Data Index: 414575 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8666. Min Act: -0.0000

Data Index: 474044 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1817797 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9291. Min Act: -0.0000

Data Index: 928923 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8715. Min Act: 0.0000

Data Index: 1137981 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8064. Min Act: -0.0000

Data Index: 428199 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8525. Min Act: -0.0000

Data Index: 650624 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.8730. Min Act: 0.0000

Data Index: 413061 (The Pile)

Max Activating Token Index: 439