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

Dataset: The Pile

Neuron 216 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: 3.1062. Min Range: -3.1062

Max Act: 3.1062. Min Act: -0.0000

Data Index: 506139 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.8022. Min Act: -0.0000

Data Index: 225380 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.6825. Min Act: -0.0000

Data Index: 307341 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.4643. Min Act: -0.0000

Data Index: 1117880 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.3170. Min Act: -0.0000

Data Index: 955005 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.4410. Min Act: -0.0000

Data Index: 1526804 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.2596. Min Act: -0.0000

Data Index: 1494981 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.3240. Min Act: -0.0000

Data Index: 272373 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.1817. Min Act: -0.0000

Data Index: 877176 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.2626. Min Act: -0.0000

Data Index: 1603508 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.3599. Min Act: -0.0000

Data Index: 1026987 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.1521. Min Act: -0.0000

Data Index: 527121 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.3280. Min Act: -0.0000

Data Index: 1401759 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.3030. Min Act: -0.0000

Data Index: 1365274 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.1825. Min Act: -0.0000

Data Index: 315594 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.0596. Min Act: -0.0000

Data Index: 1694497 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.1720. Min Act: -0.0000

Data Index: 267709 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 3.1062. Min Range: -3.1062

Max Act: 2.2678. Min Act: -0.0000

Data Index: 1147314 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 3.1062. Min Range: -3.1062

Max Act: 1.9985. Min Act: -0.0000

Data Index: 1132054 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 3.1062. Min Range: -3.1062

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1962364 (The Pile)

Max Activating Token Index: 530