Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.9600. Min Act: -0.0000

Data Index: 1429131 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.5339. Min Act: -0.0000

Data Index: 1498772 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.2666. Min Act: -0.0000

Data Index: 1474567 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1425999 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.1617. Min Act: -0.0000

Data Index: 1461064 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.1391. Min Act: -0.0000

Data Index: 1405498 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0240. Min Act: -0.0000

Data Index: 1570571 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1369086 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1446602 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0780. Min Act: -0.0000

Data Index: 1474583 (Python Code)

Max Activating Token Index: 481

Text #10

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0561. Min Act: -0.0000

Data Index: 1615320 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0398. Min Act: -0.0000

Data Index: 1601398 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.1402. Min Act: -0.0000

Data Index: 1504509 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0366. Min Act: -0.0000

Data Index: 1557963 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0056. Min Act: -0.0000

Data Index: 1388183 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 2.9600. Min Range: -2.9600

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1420944 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 2.9600. Min Range: -2.9600

Max Act: 1.9810. Min Act: -0.0000

Data Index: 1636819 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0954. Min Act: -0.0000

Data Index: 1500446 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1410263 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 2.9600. Min Range: -2.9600

Max Act: 2.0792. Min Act: -0.0000

Data Index: 1603305 (Python Code)

Max Activating Token Index: 163