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

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

Neuron 1004 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1116. Min Act: -0.0001

Data Index: 146999 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0796. Min Act: -0.0001

Data Index: 92624 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0799. Min Act: -0.0001

Data Index: 174253 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0822. Min Act: -0.0001

Data Index: 794724 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1188861 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1220479 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0683. Min Act: -0.0001

Data Index: 643373 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1170045 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0724. Min Act: -0.0001

Data Index: 409864 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1214951 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0698. Min Act: -0.0001

Data Index: 616913 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1001344 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1113437 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1027469 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0668. Min Act: -0.0001

Data Index: 367849 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0680. Min Act: -0.0001

Data Index: 274109 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0725. Min Act: -0.0001

Data Index: 846633 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1283461 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0596. Min Act: -0.0001

Data Index: 480706 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0636. Min Act: -0.0001

Data Index: 827599 (C4 (Web Text))

Max Activating Token Index: 11