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

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

Neuron 162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5688. Min Act: -0.0000

Data Index: 641685 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5655. Min Act: -0.0001

Data Index: 1035854 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5018. Min Act: -0.0001

Data Index: 622790 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5389. Min Act: -0.0001

Data Index: 646614 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4964. Min Act: -0.0001

Data Index: 291581 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4996. Min Act: -0.0000

Data Index: 257951 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4942. Min Act: -0.0001

Data Index: 351992 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5077. Min Act: -0.0000

Data Index: 952903 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4955. Min Act: -0.0000

Data Index: 858548 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4453. Min Act: -0.0000

Data Index: 504032 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4818. Min Act: -0.0001

Data Index: 345322 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4772. Min Act: -0.0000

Data Index: 430007 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1241220 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4534. Min Act: -0.0001

Data Index: 490192 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4702. Min Act: -0.0000

Data Index: 706319 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1212171 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1152292 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4438. Min Act: -0.0001

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1318978 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4638. Min Act: -0.0001

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 803