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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4298 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.9624. Min Act: -0.0000

Data Index: 132755 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 2.0193. Min Range: -2.0193

Max Act: 2.0193. Min Act: -0.0000

Data Index: 660871 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.8469. Min Act: -0.0000

Data Index: 14786 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.7669. Min Act: -0.0000

Data Index: 367170 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.7062. Min Act: -0.0000

Data Index: 944656 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.7815. Min Act: -0.0000

Data Index: 876166 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.8498. Min Act: -0.0000

Data Index: 244690 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.7433. Min Act: -0.0000

Data Index: 687934 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6115. Min Act: -0.0000

Data Index: 603515 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6098. Min Act: -0.0000

Data Index: 157158 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1070913 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6517. Min Act: -0.0000

Data Index: 305813 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6630. Min Act: -0.0000

Data Index: 60041 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6393. Min Act: -0.0000

Data Index: 975904 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6607. Min Act: -0.0000

Data Index: 548935 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.5561. Min Act: -0.0000

Data Index: 413805 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.5920. Min Act: -0.0000

Data Index: 307245 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6243. Min Act: -0.0000

Data Index: 519886 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6629. Min Act: -0.0000

Data Index: 55154 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 2.0193. Min Range: -2.0193

Max Act: 1.6144. Min Act: -0.0001

Data Index: 1096323 (C4 (Web Text))

Max Activating Token Index: 41