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

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

Neuron 2986 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0116. Min Range: -4.0116

Max Act: 4.0116. Min Act: -0.0000

Data Index: 1450198 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.8578. Min Act: -0.0000

Data Index: 1510232 (Python Code)

Max Activating Token Index: 911

Text #2

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2707. Min Act: -0.0000

Data Index: 1474247 (Python Code)

Max Activating Token Index: 801

Text #3

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2695. Min Act: -0.0000

Data Index: 1603612 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2567. Min Act: -0.0000

Data Index: 1654483 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2042. Min Act: -0.0000

Data Index: 1652031 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.3046. Min Act: -0.0000

Data Index: 1483988 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2305. Min Act: -0.0000

Data Index: 1576772 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.3636. Min Act: -0.0000

Data Index: 1600011 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.3458. Min Act: -0.0000

Data Index: 1407830 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2041. Min Act: -0.0000

Data Index: 1359880 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.1705. Min Act: -0.0000

Data Index: 1488552 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.1776. Min Act: -0.0000

Data Index: 1548909 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.1901. Min Act: -0.0000

Data Index: 1478454 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.1376. Min Act: -0.0000

Data Index: 1506860 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1632188 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2467. Min Act: -0.0000

Data Index: 1528233 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.0865. Min Act: -0.0000

Data Index: 1463215 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.9210. Min Act: -0.0000

Data Index: 1456922 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.0508. Min Act: -0.0000

Data Index: 1642582 (Python Code)

Max Activating Token Index: 164