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

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

Neuron 1571 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.9191. Min Act: -0.0001

Data Index: 1560080 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.8437. Min Act: -0.0001

Data Index: 1546651 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.9381. Min Act: -0.0001

Data Index: 1516018 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7549. Min Act: -0.0001

Data Index: 1589990 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7707. Min Act: -0.0001

Data Index: 1381358 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6708. Min Act: -0.0001

Data Index: 1624516 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6114. Min Act: -0.0001

Data Index: 1588001 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6851. Min Act: -0.0001

Data Index: 1434466 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6170. Min Act: -0.0001

Data Index: 1488531 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6703. Min Act: -0.0001

Data Index: 1492508 (Python Code)

Max Activating Token Index: 531

Text #10

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6154. Min Act: -0.0001

Data Index: 1541058 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6459. Min Act: -0.0001

Data Index: 1439626 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6869. Min Act: -0.0001

Data Index: 1608004 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6687. Min Act: -0.0001

Data Index: 1588873 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6591. Min Act: -0.0001

Data Index: 1588912 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.5776. Min Act: -0.0001

Data Index: 1483973 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4976. Min Act: -0.0001

Data Index: 1601877 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.5389. Min Act: -0.0001

Data Index: 1492460 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4947. Min Act: -0.0001

Data Index: 1408652 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4919. Min Act: -0.0001

Data Index: 1515917 (Python Code)

Max Activating Token Index: 49