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

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

Neuron 1919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1651035 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1461170 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4770. Min Act: -0.0001

Data Index: 1381990 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4480. Min Act: -0.0000

Data Index: 502448 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4565. Min Act: -0.0001

Data Index: 1607631 (Python Code)

Max Activating Token Index: 787

Text #5

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1618759 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1366469 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1629398 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3985. Min Act: -0.0001

Data Index: 1600242 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1376558 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1368574 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3515. Min Act: -0.0001

Data Index: 1516769 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1503583 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1452883 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1577589 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3635. Min Act: -0.0001

Data Index: 1436764 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1564394 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1457830 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3306. Min Act: -0.0000

Data Index: 870759 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1628301 (Python Code)

Max Activating Token Index: 401