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

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

Neuron 4977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1209937 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0000

Data Index: 653479 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1013. Min Act: -0.0001

Data Index: 487026 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0883. Min Act: -0.0000

Data Index: 382092 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0967. Min Act: -0.0000

Data Index: 623958 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0776. Min Act: -0.0000

Data Index: 29413 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1320522 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0789. Min Act: -0.0000

Data Index: 895412 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1090389 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0848. Min Act: -0.0000

Data Index: 660622 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0768. Min Act: -0.0000

Data Index: 365718 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0795. Min Act: -0.0000

Data Index: 14632 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0695. Min Act: -0.0000

Data Index: 776891 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0741. Min Act: -0.0000

Data Index: 560702 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0759. Min Act: -0.0000

Data Index: 597475 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0749. Min Act: -0.0000

Data Index: 139794 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0693. Min Act: -0.0000

Data Index: 306055 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1026777 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0736. Min Act: -0.0000

Data Index: 851123 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0678. Min Act: -0.0000

Data Index: 580880 (C4 (Web Text))

Max Activating Token Index: 431