Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0003

Data Index: 647422 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0745. Min Act: -0.0003

Data Index: 748848 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0763. Min Act: -0.0003

Data Index: 317629 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1114809 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0690. Min Act: -0.0003

Data Index: 707745 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0703. Min Act: -0.0003

Data Index: 389139 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1057308 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0676. Min Act: -0.0003

Data Index: 254542 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0670. Min Act: -0.0003

Data Index: 307576 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1191455 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0692. Min Act: -0.0003

Data Index: 794964 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0685. Min Act: -0.0003

Data Index: 415530 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1257900 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1098638 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0721. Min Act: -0.0003

Data Index: 48076 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0668. Min Act: -0.0003

Data Index: 630790 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0646. Min Act: -0.0003

Data Index: 503288 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0643. Min Act: -0.0004

Data Index: 574158 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0689. Min Act: -0.0003

Data Index: 538149 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0662. Min Act: -0.0003

Data Index: 852639 (C4 (Web Text))

Max Activating Token Index: 173