Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0728. Min Act: -0.0003

Data Index: 7271 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0003

Data Index: 442309 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1024819 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0782. Min Act: -0.0003

Data Index: 771532 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1189385 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0709. Min Act: -0.0003

Data Index: 611865 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1332995 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0663. Min Act: -0.0003

Data Index: 956652 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0654. Min Act: -0.0003

Data Index: 271623 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0652. Min Act: -0.0003

Data Index: 384030 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0697. Min Act: -0.0003

Data Index: 675963 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0613. Min Act: -0.0003

Data Index: 864913 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0628. Min Act: -0.0003

Data Index: 274644 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0629. Min Act: -0.0003

Data Index: 956945 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0602. Min Act: -0.0003

Data Index: 810196 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0590. Min Act: -0.0003

Data Index: 321154 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0618. Min Act: -0.0003

Data Index: 144335 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0607. Min Act: -0.0003

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0624. Min Act: -0.0003

Data Index: 353503 (C4 (Web Text))

Max Activating Token Index: 234