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

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

Neuron 3089 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.6627. Min Act: -0.0001

Data Index: 588923 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1566366 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4728. Min Act: -0.0001

Data Index: 1603680 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1211549 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4412. Min Act: -0.0001

Data Index: 1108509 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4395. Min Act: -0.0001

Data Index: 1563259 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4392. Min Act: -0.0001

Data Index: 1438752 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1363094 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.3929. Min Act: -0.0001

Data Index: 1430890 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4030. Min Act: -0.0001

Data Index: 431730 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1607616 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4290. Min Act: -0.0001

Data Index: 146187 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4555. Min Act: -0.0001

Data Index: 218289 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.3789. Min Act: -0.0001

Data Index: 1433729 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4384. Min Act: -0.0001

Data Index: 566039 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1652193 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1512168 (Python Code)

Max Activating Token Index: 543

Text #17

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4019. Min Act: -0.0001

Data Index: 1470552 (Python Code)

Max Activating Token Index: 571

Text #18

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.3990. Min Act: -0.0001

Data Index: 1394737 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.6627. Min Range: -0.6627

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1478974 (Python Code)

Max Activating Token Index: 460