Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1473 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0006

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0705. Min Act: -0.0006

Data Index: 273985 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0703. Min Act: -0.0006

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0680. Min Act: -0.0006

Data Index: 392484 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0696. Min Act: -0.0006

Data Index: 1003051 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0679. Min Act: -0.0005

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0660. Min Act: -0.0005

Data Index: 533581 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0664. Min Act: -0.0006

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0650. Min Act: -0.0006

Data Index: 472672 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0650. Min Act: -0.0006

Data Index: 90857 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0649. Min Act: -0.0006

Data Index: 333833 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0660. Min Act: -0.0006

Data Index: 70814 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0671. Min Act: -0.0006

Data Index: 802741 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0640. Min Act: -0.0006

Data Index: 390746 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0625. Min Act: -0.0006

Data Index: 818805 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0636. Min Act: -0.0006

Data Index: 184842 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0634. Min Act: -0.0006

Data Index: 98553 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0633. Min Act: -0.0006

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0629. Min Act: -0.0006

Data Index: 1338352 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0614. Min Act: -0.0006

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 40