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

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

Neuron 4444 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1664. Min Range: -2.1664

Max Act: 2.1664. Min Act: -0.0000

Data Index: 112593 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 2.1664. Min Range: -2.1664

Max Act: 2.0090. Min Act: -0.0000

Data Index: 515593 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.8601. Min Act: -0.0000

Data Index: 734207 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6851. Min Act: -0.0000

Data Index: 1278525 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6451. Min Act: -0.0000

Data Index: 493344 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1089346 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1051007 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6551. Min Act: -0.0000

Data Index: 1046125 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6354. Min Act: -0.0000

Data Index: 523521 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6296. Min Act: -0.0000

Data Index: 23862 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6344. Min Act: -0.0000

Data Index: 599112 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6125. Min Act: -0.0000

Data Index: 1099015 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.5979. Min Act: -0.0000

Data Index: 30448 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.5776. Min Act: -0.0000

Data Index: 434996 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.7032. Min Act: -0.0000

Data Index: 588602 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6076. Min Act: -0.0000

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.4463. Min Act: -0.0000

Data Index: 251987 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.6536. Min Act: 0.0000

Data Index: 89972 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.5516. Min Act: -0.0000

Data Index: 451215 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 2.1664. Min Range: -2.1664

Max Act: 1.4774. Min Act: 0.0000

Data Index: 514484 (C4 (Web Text))

Max Activating Token Index: 414