Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1173066 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0659. Min Act: -0.0002

Data Index: 226916 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1142825 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0655. Min Act: -0.0002

Data Index: 199575 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0625. Min Act: -0.0002

Data Index: 374701 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0626. Min Act: -0.0002

Data Index: 743556 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0623. Min Act: -0.0002

Data Index: 261569 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0598. Min Act: -0.0002

Data Index: 795490 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0538. Min Act: -0.0002

Data Index: 949045 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1044000 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1204385 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0533. Min Act: -0.0002

Data Index: 807780 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1073990 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1191039 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1220281 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0522. Min Act: -0.0002

Data Index: 721823 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0536. Min Act: -0.0002

Data Index: 771225 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1311397 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0508. Min Act: -0.0002

Data Index: 991003 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0505. Min Act: -0.0002

Data Index: 516667 (C4 (Web Text))

Max Activating Token Index: 700