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

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

Neuron 275 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0001

Data Index: 329289 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0744. Min Act: -0.0001

Data Index: 832142 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0731. Min Act: -0.0001

Data Index: 456841 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0742. Min Act: -0.0001

Data Index: 266819 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1233726 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0711. Min Act: -0.0001

Data Index: 443565 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0711. Min Act: -0.0001

Data Index: 729458 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1006924 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1189104 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0675. Min Act: -0.0001

Data Index: 275280 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0651. Min Act: -0.0001

Data Index: 654420 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1215027 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0656. Min Act: -0.0001

Data Index: 588810 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0633. Min Act: -0.0001

Data Index: 118219 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1000749 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0631. Min Act: -0.0001

Data Index: 732189 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1053446 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1237274 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0646. Min Act: -0.0001

Data Index: 92970 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0653. Min Act: -0.0001

Data Index: 270036 (C4 (Web Text))

Max Activating Token Index: 26