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

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

Neuron 3269 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4637. Min Act: -0.0001

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3378. Min Act: -0.0002

Data Index: 1300789 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4065. Min Act: -0.0002

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4749. Min Act: -0.0002

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4636. Min Act: -0.0001

Data Index: 1634209 (Python Code)

Max Activating Token Index: 873

Text #5

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3392. Min Act: -0.0001

Data Index: 1618936 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4917. Min Act: -0.0002

Data Index: 744844 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3870. Min Act: -0.0001

Data Index: 1382778 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.4193. Min Act: -0.0001

Data Index: 1548797 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3903. Min Act: -0.0001

Data Index: 436950 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3434. Min Act: -0.0001

Data Index: 1545165 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3435. Min Act: -0.0001

Data Index: 1526801 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3212. Min Act: -0.0001

Data Index: 1466949 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.2360. Min Act: -0.0001

Data Index: 1381521 (Python Code)

Max Activating Token Index: 951

Text #14

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.2668. Min Act: -0.0001

Data Index: 1447512 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.2236. Min Act: -0.0001

Data Index: 1441108 (Python Code)

Max Activating Token Index: 909

Text #16

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.2902. Min Act: -0.0001

Data Index: 1416549 (Python Code)

Max Activating Token Index: 484

Text #17

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3277. Min Act: -0.0001

Data Index: 1596946 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.2435. Min Act: -0.0001

Data Index: 1517825 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 1.4917. Min Range: -1.4917

Max Act: 1.3273. Min Act: -0.0001

Data Index: 1427695 (Python Code)

Max Activating Token Index: 740