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

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

Neuron 3482 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0003

Data Index: 1605224 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5406. Min Act: -0.0003

Data Index: 1412994 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4814. Min Act: -0.0003

Data Index: 1548661 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4852. Min Act: -0.0003

Data Index: 1568131 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4838. Min Act: -0.0003

Data Index: 1413254 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4690. Min Act: -0.0003

Data Index: 1578480 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4629. Min Act: -0.0003

Data Index: 1430381 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4660. Min Act: -0.0003

Data Index: 1635108 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4497. Min Act: -0.0003

Data Index: 1438124 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4318. Min Act: -0.0003

Data Index: 1387526 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4442. Min Act: -0.0003

Data Index: 1419848 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4459. Min Act: -0.0003

Data Index: 1429501 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4304. Min Act: -0.0003

Data Index: 1410374 (Python Code)

Max Activating Token Index: 488

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4281. Min Act: -0.0003

Data Index: 1492133 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.3873. Min Act: -0.0003

Data Index: 1652746 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4269. Min Act: -0.0003

Data Index: 1407159 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4086. Min Act: -0.0003

Data Index: 1486412 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4206. Min Act: -0.0003

Data Index: 1451416 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.3967. Min Act: -0.0003

Data Index: 1404011 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.3961. Min Act: -0.0003

Data Index: 1485498 (Python Code)

Max Activating Token Index: 12